Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2602 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6899. Min Range: -6.6899
Max Act: 6.6899. Min Act: -0.1700
Data Index: 1156764 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6899. Min Range: -6.6899
Max Act: 6.6587. Min Act: -0.1700
Data Index: 3832235 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6899. Min Range: -6.6899
Max Act: 6.4399. Min Act: -0.1700
Data Index: 6861004 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6899. Min Range: -6.6899
Max Act: 6.4399. Min Act: -0.1700
Data Index: 1623221 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6899. Min Range: -6.6899
Max Act: 6.4087. Min Act: -0.1700
Data Index: 6235242 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6899. Min Range: -6.6899
Max Act: 6.4087. Min Act: -0.1700
Data Index: 8369209 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6899. Min Range: -6.6899
Max Act: 6.4399. Min Act: -0.1700
Data Index: 7566638 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6899. Min Range: -6.6899
Max Act: 6.3774. Min Act: -0.1700
Data Index: 5617250 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6899. Min Range: -6.6899
Max Act: 6.3462. Min Act: -0.1700
Data Index: 7164748 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6899. Min Range: -6.6899
Max Act: 6.3149. Min Act: -0.1700
Data Index: 223635 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6899. Min Range: -6.6899
Max Act: 6.3149. Min Act: -0.1700
Data Index: 2950632 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6899. Min Range: -6.6899
Max Act: 6.3149. Min Act: -0.1700
Data Index: 7711034 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6899. Min Range: -6.6899
Max Act: 6.3149. Min Act: -0.1700
Data Index: 1179777 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6899. Min Range: -6.6899
Max Act: 6.3149. Min Act: -0.1700
Data Index: 5736523 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6899. Min Range: -6.6899
Max Act: 6.2837. Min Act: -0.1700
Data Index: 6116354 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6899. Min Range: -6.6899
Max Act: 6.3149. Min Act: -0.1700
Data Index: 6159611 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6899. Min Range: -6.6899
Max Act: 6.2524. Min Act: -0.1700
Data Index: 1729942 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6899. Min Range: -6.6899
Max Act: 6.2524. Min Act: -0.1700
Data Index: 1020849 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6899. Min Range: -6.6899
Max Act: 6.2524. Min Act: -0.1700
Data Index: 2433930 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6899. Min Range: -6.6899
Max Act: 6.2212. Min Act: -0.1700
Data Index: 5080948 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19