Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4623 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0564. Min Range: -7.0564
Max Act: 7.0564. Min Act: -0.1700
Data Index: 7378947 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0564. Min Range: -7.0564
Max Act: 6.8689. Min Act: -0.1700
Data Index: 4331121 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0564. Min Range: -7.0564
Max Act: 6.6189. Min Act: -0.1700
Data Index: 1183082 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0564. Min Range: -7.0564
Max Act: 6.5564. Min Act: -0.1700
Data Index: 5397363 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0564. Min Range: -7.0564
Max Act: 6.5252. Min Act: -0.1700
Data Index: 1603784 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0564. Min Range: -7.0564
Max Act: 6.5252. Min Act: -0.1700
Data Index: 1162816 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0564. Min Range: -7.0564
Max Act: 6.4627. Min Act: -0.1700
Data Index: 6171469 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0564. Min Range: -7.0564
Max Act: 6.4939. Min Act: -0.1700
Data Index: 3104589 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0564. Min Range: -7.0564
Max Act: 6.4627. Min Act: -0.1700
Data Index: 4096672 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0564. Min Range: -7.0564
Max Act: 6.4314. Min Act: -0.1700
Data Index: 4127040 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0564. Min Range: -7.0564
Max Act: 6.4002. Min Act: -0.1700
Data Index: 717828 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0564. Min Range: -7.0564
Max Act: 6.4002. Min Act: -0.1700
Data Index: 4254842 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0564. Min Range: -7.0564
Max Act: 6.4002. Min Act: -0.1700
Data Index: 8025208 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0564. Min Range: -7.0564
Max Act: 6.3689. Min Act: -0.1700
Data Index: 5345895 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0564. Min Range: -7.0564
Max Act: 6.3689. Min Act: -0.1700
Data Index: 6626798 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0564. Min Range: -7.0564
Max Act: 6.3377. Min Act: -0.1700
Data Index: 8271555 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0564. Min Range: -7.0564
Max Act: 6.3064. Min Act: -0.1700
Data Index: 6943513 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0564. Min Range: -7.0564
Max Act: 6.3064. Min Act: -0.1700
Data Index: 215406 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0564. Min Range: -7.0564
Max Act: 6.3064. Min Act: -0.1700
Data Index: 4850706 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0564. Min Range: -7.0564
Max Act: 6.3064. Min Act: -0.1700
Data Index: 2115789 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19