Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 816 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.4902. Min Range: -8.4902
Max Act: 8.4902. Min Act: -0.1700
Data Index: 8407408 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4902. Min Range: -8.4902
Max Act: 8.0527. Min Act: -0.1700
Data Index: 7243228 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4902. Min Range: -8.4902
Max Act: 7.7714. Min Act: -0.1700
Data Index: 5479923 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4902. Min Range: -8.4902
Max Act: 7.7089. Min Act: -0.1700
Data Index: 5319437 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4902. Min Range: -8.4902
Max Act: 7.7402. Min Act: -0.1700
Data Index: 41524 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4902. Min Range: -8.4902
Max Act: 7.7402. Min Act: -0.1700
Data Index: 551280 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4902. Min Range: -8.4902
Max Act: 7.7089. Min Act: -0.1700
Data Index: 2755 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4902. Min Range: -8.4902
Max Act: 7.6152. Min Act: -0.1700
Data Index: 8417215 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4902. Min Range: -8.4902
Max Act: 7.6464. Min Act: -0.1700
Data Index: 566494 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4902. Min Range: -8.4902
Max Act: 7.6152. Min Act: -0.1700
Data Index: 7169107 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4902. Min Range: -8.4902
Max Act: 7.6152. Min Act: -0.1700
Data Index: 6989434 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4902. Min Range: -8.4902
Max Act: 7.5839. Min Act: -0.1700
Data Index: 2192747 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4902. Min Range: -8.4902
Max Act: 7.5839. Min Act: -0.1700
Data Index: 7764155 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4902. Min Range: -8.4902
Max Act: 7.5527. Min Act: -0.1700
Data Index: 4815302 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4902. Min Range: -8.4902
Max Act: 7.5527. Min Act: -0.1700
Data Index: 4423594 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4902. Min Range: -8.4902
Max Act: 7.5527. Min Act: -0.1700
Data Index: 7956508 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4902. Min Range: -8.4902
Max Act: 7.5214. Min Act: -0.1700
Data Index: 4066721 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4902. Min Range: -8.4902
Max Act: 7.5214. Min Act: -0.1700
Data Index: 3579150 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4902. Min Range: -8.4902
Max Act: 7.4902. Min Act: -0.1700
Data Index: 4815312 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4902. Min Range: -8.4902
Max Act: 7.4902. Min Act: -0.1700
Data Index: 5661353 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #19