Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3246 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9130. Min Range: -4.9130
Max Act: 4.9130. Min Act: -0.1700
Data Index: 5427595 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9130. Min Range: -4.9130
Max Act: 4.8818. Min Act: -0.1700
Data Index: 3049124 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9130. Min Range: -4.9130
Max Act: 4.7880. Min Act: -0.1700
Data Index: 8110184 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9130. Min Range: -4.9130
Max Act: 4.6630. Min Act: -0.1700
Data Index: 7603530 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9130. Min Range: -4.9130
Max Act: 4.7255. Min Act: -0.1700
Data Index: 3289955 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9130. Min Range: -4.9130
Max Act: 4.6318. Min Act: -0.1700
Data Index: 8538716 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9130. Min Range: -4.9130
Max Act: 4.6630. Min Act: -0.1700
Data Index: 2115533 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9130. Min Range: -4.9130
Max Act: 4.6943. Min Act: -0.1700
Data Index: 878526 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9130. Min Range: -4.9130
Max Act: 4.6318. Min Act: -0.1700
Data Index: 4707585 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9130. Min Range: -4.9130
Max Act: 4.6005. Min Act: -0.1700
Data Index: 5926123 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9130. Min Range: -4.9130
Max Act: 4.6005. Min Act: -0.1700
Data Index: 2751404 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9130. Min Range: -4.9130
Max Act: 4.5693. Min Act: -0.1700
Data Index: 1567951 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9130. Min Range: -4.9130
Max Act: 4.6005. Min Act: -0.1700
Data Index: 5610869 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9130. Min Range: -4.9130
Max Act: 4.5693. Min Act: -0.1700
Data Index: 6526535 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9130. Min Range: -4.9130
Max Act: 4.5693. Min Act: -0.1700
Data Index: 3172085 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9130. Min Range: -4.9130
Max Act: 4.5693. Min Act: -0.1700
Data Index: 5470565 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9130. Min Range: -4.9130
Max Act: 4.5693. Min Act: -0.1700
Data Index: 592473 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9130. Min Range: -4.9130
Max Act: 4.5380. Min Act: -0.1700
Data Index: 2260963 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9130. Min Range: -4.9130
Max Act: 4.5693. Min Act: -0.1700
Data Index: 1312664 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9130. Min Range: -4.9130
Max Act: 4.5380. Min Act: -0.1700
Data Index: 3606905 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #19