Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3729 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3009. Min Range: -7.3009
Max Act: 7.3009. Min Act: -0.1700
Data Index: 4580532 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3009. Min Range: -7.3009
Max Act: 7.2384. Min Act: -0.1700
Data Index: 3375219 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3009. Min Range: -7.3009
Max Act: 7.1759. Min Act: -0.1700
Data Index: 8173641 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3009. Min Range: -7.3009
Max Act: 6.9884. Min Act: -0.1700
Data Index: 3375217 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3009. Min Range: -7.3009
Max Act: 6.9259. Min Act: -0.1700
Data Index: 876177 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3009. Min Range: -7.3009
Max Act: 6.8321. Min Act: -0.1700
Data Index: 2298395 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3009. Min Range: -7.3009
Max Act: 6.8634. Min Act: -0.1700
Data Index: 2298394 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3009. Min Range: -7.3009
Max Act: 6.8009. Min Act: -0.1700
Data Index: 2690176 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3009. Min Range: -7.3009
Max Act: 6.7071. Min Act: -0.1700
Data Index: 3599615 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3009. Min Range: -7.3009
Max Act: 6.7384. Min Act: -0.1700
Data Index: 8413776 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3009. Min Range: -7.3009
Max Act: 6.6759. Min Act: -0.1700
Data Index: 6039084 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3009. Min Range: -7.3009
Max Act: 6.6759. Min Act: -0.1700
Data Index: 6825301 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3009. Min Range: -7.3009
Max Act: 6.6446. Min Act: -0.1700
Data Index: 221384 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3009. Min Range: -7.3009
Max Act: 6.6446. Min Act: -0.1700
Data Index: 6825298 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3009. Min Range: -7.3009
Max Act: 6.6446. Min Act: -0.1700
Data Index: 3477713 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3009. Min Range: -7.3009
Max Act: 6.6446. Min Act: -0.1700
Data Index: 3176746 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3009. Min Range: -7.3009
Max Act: 6.6134. Min Act: -0.1700
Data Index: 2459570 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3009. Min Range: -7.3009
Max Act: 6.6446. Min Act: -0.1700
Data Index: 5004923 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3009. Min Range: -7.3009
Max Act: 6.6134. Min Act: -0.1700
Data Index: 7541009 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3009. Min Range: -7.3009
Max Act: 6.6134. Min Act: -0.1700
Data Index: 2541626 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19