Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 114 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9741. Min Range: -4.9741
Max Act: 4.9741. Min Act: -0.1700
Data Index: 2150701 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9741. Min Range: -4.9741
Max Act: 4.9116. Min Act: -0.1700
Data Index: 4630301 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9741. Min Range: -4.9741
Max Act: 4.8804. Min Act: -0.1700
Data Index: 7978346 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9741. Min Range: -4.9741
Max Act: 4.8179. Min Act: -0.1700
Data Index: 5562053 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9741. Min Range: -4.9741
Max Act: 4.8179. Min Act: -0.1700
Data Index: 199246 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9741. Min Range: -4.9741
Max Act: 4.7554. Min Act: -0.1700
Data Index: 4045229 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9741. Min Range: -4.9741
Max Act: 4.7241. Min Act: -0.1700
Data Index: 7804810 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9741. Min Range: -4.9741
Max Act: 4.6929. Min Act: -0.1700
Data Index: 143366 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9741. Min Range: -4.9741
Max Act: 4.6929. Min Act: -0.1700
Data Index: 8589698 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9741. Min Range: -4.9741
Max Act: 4.6616. Min Act: -0.1700
Data Index: 160101 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9741. Min Range: -4.9741
Max Act: 4.6616. Min Act: -0.1700
Data Index: 3262071 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9741. Min Range: -4.9741
Max Act: 4.6304. Min Act: -0.1700
Data Index: 4066044 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9741. Min Range: -4.9741
Max Act: 4.5991. Min Act: -0.1700
Data Index: 8237869 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9741. Min Range: -4.9741
Max Act: 4.6304. Min Act: -0.1700
Data Index: 5167461 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9741. Min Range: -4.9741
Max Act: 4.5991. Min Act: -0.1700
Data Index: 95591 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9741. Min Range: -4.9741
Max Act: 4.5991. Min Act: -0.1700
Data Index: 6335786 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9741. Min Range: -4.9741
Max Act: 4.5991. Min Act: -0.1700
Data Index: 6877815 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9741. Min Range: -4.9741
Max Act: 4.5991. Min Act: -0.1700
Data Index: 6880525 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9741. Min Range: -4.9741
Max Act: 4.5366. Min Act: -0.1700
Data Index: 2218620 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9741. Min Range: -4.9741
Max Act: 4.5679. Min Act: -0.1700
Data Index: 885465 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19