Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5105 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1149. Min Range: -6.1149
Max Act: 6.1149. Min Act: -0.1700
Data Index: 7507522 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1149. Min Range: -6.1149
Max Act: 5.8649. Min Act: -0.1700
Data Index: 1275003 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1149. Min Range: -6.1149
Max Act: 5.8337. Min Act: -0.1700
Data Index: 4890748 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1149. Min Range: -6.1149
Max Act: 5.7399. Min Act: -0.1700
Data Index: 5725905 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1149. Min Range: -6.1149
Max Act: 5.7087. Min Act: -0.1700
Data Index: 2896000 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1149. Min Range: -6.1149
Max Act: 5.6462. Min Act: -0.1700
Data Index: 6707446 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1149. Min Range: -6.1149
Max Act: 5.6149. Min Act: -0.1700
Data Index: 7946535 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1149. Min Range: -6.1149
Max Act: 5.6149. Min Act: -0.1700
Data Index: 6321031 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1149. Min Range: -6.1149
Max Act: 5.5837. Min Act: -0.1700
Data Index: 3623256 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1149. Min Range: -6.1149
Max Act: 5.5837. Min Act: -0.1700
Data Index: 72524 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1149. Min Range: -6.1149
Max Act: 5.5837. Min Act: -0.1700
Data Index: 6915115 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1149. Min Range: -6.1149
Max Act: 5.5524. Min Act: -0.1700
Data Index: 4507677 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1149. Min Range: -6.1149
Max Act: 5.5524. Min Act: -0.1700
Data Index: 3951311 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1149. Min Range: -6.1149
Max Act: 5.5212. Min Act: -0.1700
Data Index: 3219713 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1149. Min Range: -6.1149
Max Act: 5.5524. Min Act: -0.1700
Data Index: 7031973 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1149. Min Range: -6.1149
Max Act: 5.4899. Min Act: -0.1700
Data Index: 7158469 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1149. Min Range: -6.1149
Max Act: 5.4899. Min Act: -0.1700
Data Index: 5989246 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1149. Min Range: -6.1149
Max Act: 5.4587. Min Act: -0.1700
Data Index: 8598941 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1149. Min Range: -6.1149
Max Act: 5.4274. Min Act: -0.1700
Data Index: 2689172 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1149. Min Range: -6.1149
Max Act: 5.4587. Min Act: -0.1700
Data Index: 5118602 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19