Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1971 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9053. Min Range: -6.9053
Max Act: 6.9053. Min Act: -0.1700
Data Index: 309166 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9053. Min Range: -6.9053
Max Act: 6.9053. Min Act: -0.1700
Data Index: 3626671 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9053. Min Range: -6.9053
Max Act: 6.7178. Min Act: -0.1700
Data Index: 3114727 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9053. Min Range: -6.9053
Max Act: 6.6865. Min Act: -0.1700
Data Index: 6524255 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9053. Min Range: -6.9053
Max Act: 6.6865. Min Act: -0.1700
Data Index: 6600153 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9053. Min Range: -6.9053
Max Act: 6.6865. Min Act: -0.1700
Data Index: 7227753 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9053. Min Range: -6.9053
Max Act: 6.6553. Min Act: -0.1700
Data Index: 4617695 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9053. Min Range: -6.9053
Max Act: 6.6865. Min Act: -0.1700
Data Index: 3681048 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9053. Min Range: -6.9053
Max Act: 6.6240. Min Act: -0.1700
Data Index: 7530701 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9053. Min Range: -6.9053
Max Act: 6.6240. Min Act: -0.1700
Data Index: 304765 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9053. Min Range: -6.9053
Max Act: 6.5615. Min Act: -0.1700
Data Index: 4461321 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9053. Min Range: -6.9053
Max Act: 6.5303. Min Act: -0.1700
Data Index: 628634 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9053. Min Range: -6.9053
Max Act: 6.5303. Min Act: -0.1700
Data Index: 4241116 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9053. Min Range: -6.9053
Max Act: 6.4990. Min Act: -0.1700
Data Index: 3766900 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9053. Min Range: -6.9053
Max Act: 6.4990. Min Act: -0.1700
Data Index: 6895261 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9053. Min Range: -6.9053
Max Act: 6.4990. Min Act: -0.1700
Data Index: 5064749 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9053. Min Range: -6.9053
Max Act: 6.5303. Min Act: -0.1700
Data Index: 357447 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9053. Min Range: -6.9053
Max Act: 6.5303. Min Act: -0.1700
Data Index: 1910471 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9053. Min Range: -6.9053
Max Act: 6.4678. Min Act: -0.1700
Data Index: 5426971 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9053. Min Range: -6.9053
Max Act: 6.4678. Min Act: -0.1700
Data Index: 720850 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #19