Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3951 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.3359. Min Range: -2.3359
Max Act: 2.3359. Min Act: -0.1700
Data Index: 1444772 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3359. Min Range: -2.3359
Max Act: 2.3195. Min Act: -0.1700
Data Index: 2317141 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3359. Min Range: -2.3359
Max Act: 2.3031. Min Act: -0.1700
Data Index: 4952601 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3359. Min Range: -2.3359
Max Act: 2.2866. Min Act: -0.1700
Data Index: 533844 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3359. Min Range: -2.3359
Max Act: 2.2866. Min Act: -0.1700
Data Index: 1489360 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3359. Min Range: -2.3359
Max Act: 2.2701. Min Act: -0.1700
Data Index: 2617143 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3359. Min Range: -2.3359
Max Act: 2.3031. Min Act: -0.1700
Data Index: 2592011 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3359. Min Range: -2.3359
Max Act: 2.2866. Min Act: -0.1700
Data Index: 5000157 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3359. Min Range: -2.3359
Max Act: 2.2866. Min Act: -0.1700
Data Index: 7387813 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3359. Min Range: -2.3359
Max Act: 2.2866. Min Act: -0.1700
Data Index: 7285614 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3359. Min Range: -2.3359
Max Act: 2.2701. Min Act: -0.1700
Data Index: 4083198 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3359. Min Range: -2.3359
Max Act: 2.2536. Min Act: -0.1700
Data Index: 2034855 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3359. Min Range: -2.3359
Max Act: 2.2536. Min Act: -0.1700
Data Index: 2887470 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3359. Min Range: -2.3359
Max Act: 2.2371. Min Act: -0.1700
Data Index: 5357332 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3359. Min Range: -2.3359
Max Act: 2.2701. Min Act: -0.1700
Data Index: 1554468 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3359. Min Range: -2.3359
Max Act: 2.2371. Min Act: -0.1700
Data Index: 533841 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3359. Min Range: -2.3359
Max Act: 2.2536. Min Act: -0.1700
Data Index: 7927235 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3359. Min Range: -2.3359
Max Act: 2.2371. Min Act: -0.1700
Data Index: 1840080 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3359. Min Range: -2.3359
Max Act: 2.2371. Min Act: -0.1700
Data Index: 1921168 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3359. Min Range: -2.3359
Max Act: 2.2371. Min Act: -0.1700
Data Index: 5660327 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #19