Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2715 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3209. Min Range: -2.3209
Max Act: 2.3209. Min Act: -0.1700
Data Index: 8250373 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3209. Min Range: -2.3209
Max Act: 2.2715. Min Act: -0.1700
Data Index: 2550166 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3209. Min Range: -2.3209
Max Act: 2.2715. Min Act: -0.1700
Data Index: 3655188 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3209. Min Range: -2.3209
Max Act: 2.2550. Min Act: -0.1700
Data Index: 6528884 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3209. Min Range: -2.3209
Max Act: 2.2385. Min Act: -0.1700
Data Index: 1049754 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3209. Min Range: -2.3209
Max Act: 2.2385. Min Act: -0.1700
Data Index: 2316108 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3209. Min Range: -2.3209
Max Act: 2.2054. Min Act: -0.1700
Data Index: 130425 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3209. Min Range: -2.3209
Max Act: 2.2220. Min Act: -0.1700
Data Index: 8284934 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3209. Min Range: -2.3209
Max Act: 2.2220. Min Act: -0.1700
Data Index: 7781427 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3209. Min Range: -2.3209
Max Act: 2.2054. Min Act: -0.1700
Data Index: 2429671 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3209. Min Range: -2.3209
Max Act: 2.1888. Min Act: -0.1700
Data Index: 6528885 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3209. Min Range: -2.3209
Max Act: 2.1888. Min Act: -0.1700
Data Index: 5298554 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3209. Min Range: -2.3209
Max Act: 2.1888. Min Act: -0.1700
Data Index: 4152169 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3209. Min Range: -2.3209
Max Act: 2.1888. Min Act: -0.1700
Data Index: 8598654 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3209. Min Range: -2.3209
Max Act: 2.1722. Min Act: -0.1700
Data Index: 7213248 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3209. Min Range: -2.3209
Max Act: 2.1555. Min Act: -0.1700
Data Index: 7839465 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3209. Min Range: -2.3209
Max Act: 2.1555. Min Act: -0.1700
Data Index: 7828800 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3209. Min Range: -2.3209
Max Act: 2.1388. Min Act: -0.1700
Data Index: 1022007 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3209. Min Range: -2.3209
Max Act: 2.1722. Min Act: -0.1700
Data Index: 6785912 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3209. Min Range: -2.3209
Max Act: 2.1388. Min Act: -0.1700
Data Index: 3724696 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #19