Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3260 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7149. Min Range: -4.7149
Max Act: 4.7149. Min Act: -0.1700
Data Index: 8459909 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7149. Min Range: -4.7149
Max Act: 4.6837. Min Act: -0.1700
Data Index: 3894740 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7149. Min Range: -4.7149
Max Act: 4.5899. Min Act: -0.1700
Data Index: 5612786 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7149. Min Range: -4.7149
Max Act: 4.5899. Min Act: -0.1700
Data Index: 4482882 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7149. Min Range: -4.7149
Max Act: 4.5899. Min Act: -0.1700
Data Index: 6955131 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7149. Min Range: -4.7149
Max Act: 4.5899. Min Act: -0.1700
Data Index: 2989785 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7149. Min Range: -4.7149
Max Act: 4.5587. Min Act: -0.1700
Data Index: 3422381 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7149. Min Range: -4.7149
Max Act: 4.5587. Min Act: -0.1700
Data Index: 1956453 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7149. Min Range: -4.7149
Max Act: 4.5587. Min Act: -0.1700
Data Index: 4467815 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7149. Min Range: -4.7149
Max Act: 4.4962. Min Act: -0.1700
Data Index: 537223 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7149. Min Range: -4.7149
Max Act: 4.5274. Min Act: -0.1700
Data Index: 1099809 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7149. Min Range: -4.7149
Max Act: 4.4962. Min Act: -0.1700
Data Index: 6706374 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7149. Min Range: -4.7149
Max Act: 4.4962. Min Act: -0.1700
Data Index: 3494889 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7149. Min Range: -4.7149
Max Act: 4.4962. Min Act: -0.1700
Data Index: 4433045 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7149. Min Range: -4.7149
Max Act: 4.4962. Min Act: -0.1700
Data Index: 1778337 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7149. Min Range: -4.7149
Max Act: 4.4962. Min Act: -0.1700
Data Index: 7024578 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7149. Min Range: -4.7149
Max Act: 4.4649. Min Act: -0.1700
Data Index: 1778328 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7149. Min Range: -4.7149
Max Act: 4.4649. Min Act: -0.1700
Data Index: 605471 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7149. Min Range: -4.7149
Max Act: 4.4962. Min Act: -0.1700
Data Index: 7165240 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7149. Min Range: -4.7149
Max Act: 4.4649. Min Act: -0.1700
Data Index: 857548 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19