Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4864 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8712. Min Range: -6.8712
Max Act: 6.8712. Min Act: -0.1700
Data Index: 941389 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8712. Min Range: -6.8712
Max Act: 6.7774. Min Act: -0.1700
Data Index: 5804449 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8712. Min Range: -6.8712
Max Act: 6.7149. Min Act: -0.1700
Data Index: 4626297 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8712. Min Range: -6.8712
Max Act: 6.6524. Min Act: -0.1700
Data Index: 8359298 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8712. Min Range: -6.8712
Max Act: 6.6837. Min Act: -0.1700
Data Index: 901112 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8712. Min Range: -6.8712
Max Act: 6.5899. Min Act: -0.1700
Data Index: 1753365 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8712. Min Range: -6.8712
Max Act: 6.4962. Min Act: -0.1700
Data Index: 4962690 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8712. Min Range: -6.8712
Max Act: 6.4649. Min Act: -0.1700
Data Index: 3256169 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8712. Min Range: -6.8712
Max Act: 6.4337. Min Act: -0.1700
Data Index: 6947135 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8712. Min Range: -6.8712
Max Act: 6.4337. Min Act: -0.1700
Data Index: 6323549 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8712. Min Range: -6.8712
Max Act: 6.4024. Min Act: -0.1700
Data Index: 4279106 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8712. Min Range: -6.8712
Max Act: 6.4024. Min Act: -0.1700
Data Index: 2493236 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8712. Min Range: -6.8712
Max Act: 6.4337. Min Act: -0.1700
Data Index: 6657153 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8712. Min Range: -6.8712
Max Act: 6.4337. Min Act: -0.1700
Data Index: 1134133 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8712. Min Range: -6.8712
Max Act: 6.3712. Min Act: -0.1700
Data Index: 7100913 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8712. Min Range: -6.8712
Max Act: 6.4337. Min Act: -0.1700
Data Index: 1628159 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8712. Min Range: -6.8712
Max Act: 6.4024. Min Act: -0.1700
Data Index: 192579 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8712. Min Range: -6.8712
Max Act: 6.3712. Min Act: -0.1700
Data Index: 2459832 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8712. Min Range: -6.8712
Max Act: 6.4024. Min Act: -0.1700
Data Index: 4323828 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8712. Min Range: -6.8712
Max Act: 6.4024. Min Act: -0.1700
Data Index: 7715087 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #19