Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2927 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.4728. Min Range: -10.4728
Max Act: 10.4728. Min Act: -0.1700
Data Index: 5653893 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4728. Min Range: -10.4728
Max Act: 10.4103. Min Act: -0.1700
Data Index: 5571573 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4728. Min Range: -10.4728
Max Act: 10.4103. Min Act: -0.1700
Data Index: 999812 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4728. Min Range: -10.4728
Max Act: 10.4103. Min Act: -0.1700
Data Index: 3634915 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4728. Min Range: -10.4728
Max Act: 10.4103. Min Act: -0.1700
Data Index: 5014821 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4728. Min Range: -10.4728
Max Act: 10.3478. Min Act: -0.1700
Data Index: 690531 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4728. Min Range: -10.4728
Max Act: 10.3478. Min Act: -0.1700
Data Index: 499036 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4728. Min Range: -10.4728
Max Act: 10.4103. Min Act: -0.1700
Data Index: 5973371 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4728. Min Range: -10.4728
Max Act: 10.2853. Min Act: -0.1700
Data Index: 659502 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4728. Min Range: -10.4728
Max Act: 10.2228. Min Act: -0.1700
Data Index: 2366896 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4728. Min Range: -10.4728
Max Act: 10.2853. Min Act: -0.1700
Data Index: 3297028 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4728. Min Range: -10.4728
Max Act: 10.2853. Min Act: -0.1700
Data Index: 1645230 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4728. Min Range: -10.4728
Max Act: 10.2853. Min Act: -0.1700
Data Index: 3314195 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4728. Min Range: -10.4728
Max Act: 10.2228. Min Act: -0.1700
Data Index: 2596518 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4728. Min Range: -10.4728
Max Act: 10.2228. Min Act: -0.1700
Data Index: 6861564 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4728. Min Range: -10.4728
Max Act: 10.2228. Min Act: -0.1700
Data Index: 213307 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4728. Min Range: -10.4728
Max Act: 10.2228. Min Act: -0.1700
Data Index: 1803190 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4728. Min Range: -10.4728
Max Act: 10.1603. Min Act: -0.1700
Data Index: 2596517 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4728. Min Range: -10.4728
Max Act: 10.1603. Min Act: -0.1700
Data Index: 2596516 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4728. Min Range: -10.4728
Max Act: 10.1603. Min Act: -0.1700
Data Index: 850722 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19