Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3783 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6862. Min Range: -5.6862
Max Act: 5.6862. Min Act: -0.1700
Data Index: 1138472 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6862. Min Range: -5.6862
Max Act: 5.6549. Min Act: -0.1700
Data Index: 3758791 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6862. Min Range: -5.6862
Max Act: 5.6549. Min Act: -0.1700
Data Index: 8623887 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6862. Min Range: -5.6862
Max Act: 5.5612. Min Act: -0.1700
Data Index: 7393918 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6862. Min Range: -5.6862
Max Act: 5.4674. Min Act: -0.1700
Data Index: 4459464 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6862. Min Range: -5.6862
Max Act: 5.4362. Min Act: -0.1700
Data Index: 7512488 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6862. Min Range: -5.6862
Max Act: 5.4362. Min Act: -0.1700
Data Index: 6115462 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6862. Min Range: -5.6862
Max Act: 5.4049. Min Act: -0.1700
Data Index: 1730631 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6862. Min Range: -5.6862
Max Act: 5.3737. Min Act: -0.1700
Data Index: 683350 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6862. Min Range: -5.6862
Max Act: 5.3112. Min Act: -0.1700
Data Index: 2517591 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6862. Min Range: -5.6862
Max Act: 5.3112. Min Act: -0.1700
Data Index: 2461538 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6862. Min Range: -5.6862
Max Act: 5.2799. Min Act: -0.1700
Data Index: 7313215 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6862. Min Range: -5.6862
Max Act: 5.2799. Min Act: -0.1700
Data Index: 3024864 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6862. Min Range: -5.6862
Max Act: 5.2174. Min Act: -0.1700
Data Index: 1427620 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6862. Min Range: -5.6862
Max Act: 5.2174. Min Act: -0.1700
Data Index: 7512486 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6862. Min Range: -5.6862
Max Act: 5.2174. Min Act: -0.1700
Data Index: 3191000 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6862. Min Range: -5.6862
Max Act: 5.1862. Min Act: -0.1700
Data Index: 4936505 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6862. Min Range: -5.6862
Max Act: 5.1862. Min Act: -0.1700
Data Index: 5960732 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6862. Min Range: -5.6862
Max Act: 5.1862. Min Act: -0.1700
Data Index: 6361422 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6862. Min Range: -5.6862
Max Act: 5.1862. Min Act: -0.1700
Data Index: 1862910 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #19