Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4796 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2883. Min Range: -9.2883
Max Act: 9.2883. Min Act: -0.1700
Data Index: 5596118 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2883. Min Range: -9.2883
Max Act: 8.7258. Min Act: -0.1700
Data Index: 1380819 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2883. Min Range: -9.2883
Max Act: 8.6633. Min Act: -0.1700
Data Index: 8314934 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2883. Min Range: -9.2883
Max Act: 8.6008. Min Act: -0.1700
Data Index: 5674236 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2883. Min Range: -9.2883
Max Act: 8.4758. Min Act: -0.1700
Data Index: 1739297 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2883. Min Range: -9.2883
Max Act: 8.4758. Min Act: -0.1700
Data Index: 2599520 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2883. Min Range: -9.2883
Max Act: 8.4133. Min Act: -0.1700
Data Index: 982110 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2883. Min Range: -9.2883
Max Act: 8.2258. Min Act: -0.1700
Data Index: 6006897 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2883. Min Range: -9.2883
Max Act: 8.2883. Min Act: -0.1700
Data Index: 8784462 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2883. Min Range: -9.2883
Max Act: 8.2883. Min Act: -0.1700
Data Index: 4096865 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2883. Min Range: -9.2883
Max Act: 8.2883. Min Act: -0.1700
Data Index: 7994573 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2883. Min Range: -9.2883
Max Act: 8.2883. Min Act: -0.1700
Data Index: 7989260 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2883. Min Range: -9.2883
Max Act: 8.2883. Min Act: -0.1700
Data Index: 695496 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2883. Min Range: -9.2883
Max Act: 8.2258. Min Act: -0.1700
Data Index: 485780 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2883. Min Range: -9.2883
Max Act: 8.2883. Min Act: -0.1700
Data Index: 2734465 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2883. Min Range: -9.2883
Max Act: 8.1008. Min Act: -0.1700
Data Index: 6612404 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2883. Min Range: -9.2883
Max Act: 8.1008. Min Act: -0.1700
Data Index: 2328742 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2883. Min Range: -9.2883
Max Act: 8.0383. Min Act: -0.1700
Data Index: 6158313 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2883. Min Range: -9.2883
Max Act: 8.0383. Min Act: -0.1700
Data Index: 1666972 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2883. Min Range: -9.2883
Max Act: 8.0383. Min Act: -0.1700
Data Index: 2154108 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19