Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5119 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8782. Min Range: -4.8782
Max Act: 4.8782. Min Act: -0.1700
Data Index: 2769497 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8782. Min Range: -4.8782
Max Act: 4.8469. Min Act: -0.1700
Data Index: 433299 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8782. Min Range: -4.8782
Max Act: 4.7532. Min Act: -0.1700
Data Index: 2039530 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8782. Min Range: -4.8782
Max Act: 4.7219. Min Act: -0.1700
Data Index: 7924411 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8782. Min Range: -4.8782
Max Act: 4.7219. Min Act: -0.1700
Data Index: 783147 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8782. Min Range: -4.8782
Max Act: 4.7219. Min Act: -0.1700
Data Index: 4676377 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8782. Min Range: -4.8782
Max Act: 4.7219. Min Act: -0.1700
Data Index: 903295 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8782. Min Range: -4.8782
Max Act: 4.7532. Min Act: -0.1700
Data Index: 2039545 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8782. Min Range: -4.8782
Max Act: 4.6907. Min Act: -0.1700
Data Index: 2464405 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8782. Min Range: -4.8782
Max Act: 4.6907. Min Act: -0.1700
Data Index: 2810360 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8782. Min Range: -4.8782
Max Act: 4.6907. Min Act: -0.1700
Data Index: 4744793 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8782. Min Range: -4.8782
Max Act: 4.6907. Min Act: -0.1699
Data Index: 678174 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8782. Min Range: -4.8782
Max Act: 4.6594. Min Act: -0.1700
Data Index: 5166944 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8782. Min Range: -4.8782
Max Act: 4.6594. Min Act: -0.1700
Data Index: 3475061 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8782. Min Range: -4.8782
Max Act: 4.6594. Min Act: -0.1699
Data Index: 2017564 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8782. Min Range: -4.8782
Max Act: 4.6594. Min Act: -0.1700
Data Index: 2824382 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8782. Min Range: -4.8782
Max Act: 4.6282. Min Act: -0.1700
Data Index: 4477111 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8782. Min Range: -4.8782
Max Act: 4.6282. Min Act: -0.1700
Data Index: 3388249 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8782. Min Range: -4.8782
Max Act: 4.6282. Min Act: -0.1700
Data Index: 1280758 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8782. Min Range: -4.8782
Max Act: 4.6282. Min Act: -0.1700
Data Index: 4845448 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19