Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 622 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4969. Min Range: -5.4969
Max Act: 5.4969. Min Act: -0.1700
Data Index: 446068 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4969. Min Range: -5.4969
Max Act: 5.4657. Min Act: -0.1700
Data Index: 7171304 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4969. Min Range: -5.4969
Max Act: 5.4344. Min Act: -0.1700
Data Index: 6106661 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4969. Min Range: -5.4969
Max Act: 5.3719. Min Act: -0.1700
Data Index: 5850348 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4969. Min Range: -5.4969
Max Act: 5.3407. Min Act: -0.1700
Data Index: 2599783 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4969. Min Range: -5.4969
Max Act: 5.3407. Min Act: -0.1700
Data Index: 8093323 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4969. Min Range: -5.4969
Max Act: 5.3407. Min Act: -0.1700
Data Index: 4925800 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4969. Min Range: -5.4969
Max Act: 5.3407. Min Act: -0.1700
Data Index: 207828 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4969. Min Range: -5.4969
Max Act: 5.3094. Min Act: -0.1700
Data Index: 6937526 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4969. Min Range: -5.4969
Max Act: 5.2782. Min Act: -0.1700
Data Index: 2387819 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4969. Min Range: -5.4969
Max Act: 5.3094. Min Act: -0.1700
Data Index: 7968743 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4969. Min Range: -5.4969
Max Act: 5.2469. Min Act: -0.1700
Data Index: 118289 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4969. Min Range: -5.4969
Max Act: 5.2469. Min Act: -0.1700
Data Index: 1277105 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4969. Min Range: -5.4969
Max Act: 5.2469. Min Act: -0.1700
Data Index: 2325795 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4969. Min Range: -5.4969
Max Act: 5.2157. Min Act: -0.1700
Data Index: 2451515 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4969. Min Range: -5.4969
Max Act: 5.2157. Min Act: -0.1700
Data Index: 3099606 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4969. Min Range: -5.4969
Max Act: 5.2157. Min Act: -0.1700
Data Index: 7542206 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4969. Min Range: -5.4969
Max Act: 5.2157. Min Act: -0.1700
Data Index: 5212261 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4969. Min Range: -5.4969
Max Act: 5.2157. Min Act: -0.1700
Data Index: 6124520 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4969. Min Range: -5.4969
Max Act: 5.2157. Min Act: -0.1700
Data Index: 3916677 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #19