Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4651 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4933. Min Range: -4.4933
Max Act: 4.4933. Min Act: -0.1700
Data Index: 4387916 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4933. Min Range: -4.4933
Max Act: 4.4308. Min Act: -0.1700
Data Index: 2442556 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4933. Min Range: -4.4933
Max Act: 4.3683. Min Act: -0.1700
Data Index: 3412494 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4933. Min Range: -4.4933
Max Act: 4.3995. Min Act: -0.1700
Data Index: 1454300 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4933. Min Range: -4.4933
Max Act: 4.3995. Min Act: -0.1700
Data Index: 1408301 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4933. Min Range: -4.4933
Max Act: 4.3683. Min Act: -0.1700
Data Index: 3427938 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4933. Min Range: -4.4933
Max Act: 4.3370. Min Act: -0.1700
Data Index: 8145705 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4933. Min Range: -4.4933
Max Act: 4.3370. Min Act: -0.1700
Data Index: 5000224 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4933. Min Range: -4.4933
Max Act: 4.3370. Min Act: -0.1700
Data Index: 2911373 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4933. Min Range: -4.4933
Max Act: 4.3370. Min Act: -0.1700
Data Index: 5737991 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4933. Min Range: -4.4933
Max Act: 4.3058. Min Act: -0.1700
Data Index: 6120382 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4933. Min Range: -4.4933
Max Act: 4.2745. Min Act: -0.1700
Data Index: 7290320 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4933. Min Range: -4.4933
Max Act: 4.3058. Min Act: -0.1700
Data Index: 663255 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4933. Min Range: -4.4933
Max Act: 4.2745. Min Act: -0.1700
Data Index: 3260361 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4933. Min Range: -4.4933
Max Act: 4.3058. Min Act: -0.1700
Data Index: 934013 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4933. Min Range: -4.4933
Max Act: 4.2745. Min Act: -0.1700
Data Index: 375446 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4933. Min Range: -4.4933
Max Act: 4.2433. Min Act: -0.1700
Data Index: 6736337 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4933. Min Range: -4.4933
Max Act: 4.2433. Min Act: -0.1700
Data Index: 1977808 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4933. Min Range: -4.4933
Max Act: 4.2433. Min Act: -0.1700
Data Index: 5323784 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4933. Min Range: -4.4933
Max Act: 4.2745. Min Act: -0.1700
Data Index: 4410378 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #19