Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 758 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8638. Min Range: -4.8638
Max Act: 4.8638. Min Act: -0.1700
Data Index: 3721791 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8638. Min Range: -4.8638
Max Act: 4.8326. Min Act: -0.1700
Data Index: 6945690 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8638. Min Range: -4.8638
Max Act: 4.8013. Min Act: -0.1700
Data Index: 5972706 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8638. Min Range: -4.8638
Max Act: 4.8013. Min Act: -0.1700
Data Index: 2624908 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8638. Min Range: -4.8638
Max Act: 4.7701. Min Act: -0.1700
Data Index: 2849643 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8638. Min Range: -4.8638
Max Act: 4.7388. Min Act: -0.1700
Data Index: 7778789 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8638. Min Range: -4.8638
Max Act: 4.7076. Min Act: -0.1700
Data Index: 3130610 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8638. Min Range: -4.8638
Max Act: 4.7388. Min Act: -0.1700
Data Index: 2486194 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8638. Min Range: -4.8638
Max Act: 4.7076. Min Act: -0.1700
Data Index: 4382696 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8638. Min Range: -4.8638
Max Act: 4.6451. Min Act: -0.1700
Data Index: 5728226 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8638. Min Range: -4.8638
Max Act: 4.6451. Min Act: -0.1700
Data Index: 90653 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8638. Min Range: -4.8638
Max Act: 4.6451. Min Act: -0.1700
Data Index: 564128 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8638. Min Range: -4.8638
Max Act: 4.6451. Min Act: -0.1700
Data Index: 7584849 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8638. Min Range: -4.8638
Max Act: 4.6138. Min Act: -0.1700
Data Index: 3111561 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8638. Min Range: -4.8638
Max Act: 4.6451. Min Act: -0.1700
Data Index: 6752388 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8638. Min Range: -4.8638
Max Act: 4.6451. Min Act: -0.1700
Data Index: 1447514 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8638. Min Range: -4.8638
Max Act: 4.6138. Min Act: -0.1700
Data Index: 6824791 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8638. Min Range: -4.8638
Max Act: 4.6138. Min Act: -0.1700
Data Index: 379692 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8638. Min Range: -4.8638
Max Act: 4.6138. Min Act: -0.1700
Data Index: 4693546 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8638. Min Range: -4.8638
Max Act: 4.6138. Min Act: -0.1700
Data Index: 7317770 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19