Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3173 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5613. Min Range: -6.5613
Max Act: 6.5613. Min Act: -0.1700
Data Index: 8245664 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5613. Min Range: -6.5613
Max Act: 6.3738. Min Act: -0.1700
Data Index: 4709184 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5613. Min Range: -6.5613
Max Act: 6.3113. Min Act: -0.1700
Data Index: 4557477 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5613. Min Range: -6.5613
Max Act: 6.3738. Min Act: -0.1700
Data Index: 7652574 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5613. Min Range: -6.5613
Max Act: 6.3426. Min Act: -0.1700
Data Index: 2710514 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5613. Min Range: -6.5613
Max Act: 6.3426. Min Act: -0.1700
Data Index: 8289338 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5613. Min Range: -6.5613
Max Act: 6.3738. Min Act: -0.1700
Data Index: 8257969 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5613. Min Range: -6.5613
Max Act: 6.3113. Min Act: -0.1700
Data Index: 5377178 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5613. Min Range: -6.5613
Max Act: 6.2801. Min Act: -0.1700
Data Index: 3835027 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5613. Min Range: -6.5613
Max Act: 6.2801. Min Act: -0.1700
Data Index: 5566624 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5613. Min Range: -6.5613
Max Act: 6.2488. Min Act: -0.1700
Data Index: 5865858 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5613. Min Range: -6.5613
Max Act: 6.2488. Min Act: -0.1700
Data Index: 8050171 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5613. Min Range: -6.5613
Max Act: 6.2488. Min Act: -0.1700
Data Index: 3418358 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5613. Min Range: -6.5613
Max Act: 6.2488. Min Act: -0.1700
Data Index: 4184631 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5613. Min Range: -6.5613
Max Act: 6.2176. Min Act: -0.1700
Data Index: 4625987 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5613. Min Range: -6.5613
Max Act: 6.2176. Min Act: -0.1700
Data Index: 7212870 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5613. Min Range: -6.5613
Max Act: 6.1863. Min Act: -0.1700
Data Index: 3854031 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5613. Min Range: -6.5613
Max Act: 6.1863. Min Act: -0.1700
Data Index: 8673351 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5613. Min Range: -6.5613
Max Act: 6.1863. Min Act: -0.1700
Data Index: 5357868 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5613. Min Range: -6.5613
Max Act: 6.1551. Min Act: -0.1700
Data Index: 3091766 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19