Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3201 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2734. Min Range: -6.2734
Max Act: 6.2734. Min Act: -0.1700
Data Index: 2256470 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2734. Min Range: -6.2734
Max Act: 6.2422. Min Act: -0.1700
Data Index: 3626071 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2734. Min Range: -6.2734
Max Act: 6.2109. Min Act: -0.1700
Data Index: 3268084 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2734. Min Range: -6.2734
Max Act: 6.1797. Min Act: -0.1700
Data Index: 6375388 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2734. Min Range: -6.2734
Max Act: 6.1172. Min Act: -0.1700
Data Index: 1689653 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2734. Min Range: -6.2734
Max Act: 6.0547. Min Act: -0.1700
Data Index: 5799278 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2734. Min Range: -6.2734
Max Act: 6.0234. Min Act: -0.1700
Data Index: 4905821 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2734. Min Range: -6.2734
Max Act: 6.0234. Min Act: -0.1700
Data Index: 3906128 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2734. Min Range: -6.2734
Max Act: 6.0547. Min Act: -0.1700
Data Index: 7149833 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2734. Min Range: -6.2734
Max Act: 6.0234. Min Act: -0.1700
Data Index: 7662264 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2734. Min Range: -6.2734
Max Act: 5.9609. Min Act: -0.1700
Data Index: 1862311 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2734. Min Range: -6.2734
Max Act: 5.9922. Min Act: -0.1700
Data Index: 2041346 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2734. Min Range: -6.2734
Max Act: 6.0234. Min Act: -0.1700
Data Index: 4928295 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2734. Min Range: -6.2734
Max Act: 5.9297. Min Act: -0.1700
Data Index: 8304777 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2734. Min Range: -6.2734
Max Act: 5.9609. Min Act: -0.1700
Data Index: 7810978 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2734. Min Range: -6.2734
Max Act: 5.9609. Min Act: -0.1700
Data Index: 6691991 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2734. Min Range: -6.2734
Max Act: 5.9609. Min Act: -0.1700
Data Index: 8524129 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2734. Min Range: -6.2734
Max Act: 5.9609. Min Act: -0.1700
Data Index: 2041345 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2734. Min Range: -6.2734
Max Act: 5.9297. Min Act: -0.1700
Data Index: 6729679 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2734. Min Range: -6.2734
Max Act: 5.9297. Min Act: -0.1700
Data Index: 7348749 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19