Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2172 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2279. Min Range: -6.2279
Max Act: 6.2279. Min Act: -0.1700
Data Index: 8625239 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2279. Min Range: -6.2279
Max Act: 6.1966. Min Act: -0.1700
Data Index: 473731 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2279. Min Range: -6.2279
Max Act: 6.1966. Min Act: -0.1700
Data Index: 5085035 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2279. Min Range: -6.2279
Max Act: 6.1029. Min Act: -0.1700
Data Index: 5272689 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2279. Min Range: -6.2279
Max Act: 6.1029. Min Act: -0.1700
Data Index: 2676885 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2279. Min Range: -6.2279
Max Act: 6.0091. Min Act: -0.1700
Data Index: 1434720 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2279. Min Range: -6.2279
Max Act: 6.0091. Min Act: -0.1700
Data Index: 6544812 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2279. Min Range: -6.2279
Max Act: 5.9154. Min Act: -0.1700
Data Index: 8489441 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2279. Min Range: -6.2279
Max Act: 5.9779. Min Act: -0.1700
Data Index: 211837 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2279. Min Range: -6.2279
Max Act: 5.9466. Min Act: -0.1700
Data Index: 1586030 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2279. Min Range: -6.2279
Max Act: 5.9154. Min Act: -0.1700
Data Index: 7072844 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2279. Min Range: -6.2279
Max Act: 5.9154. Min Act: -0.1700
Data Index: 6414641 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2279. Min Range: -6.2279
Max Act: 5.8529. Min Act: -0.1700
Data Index: 3744660 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2279. Min Range: -6.2279
Max Act: 5.8529. Min Act: -0.1700
Data Index: 45978 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2279. Min Range: -6.2279
Max Act: 5.8529. Min Act: -0.1700
Data Index: 367011 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2279. Min Range: -6.2279
Max Act: 5.8529. Min Act: -0.1700
Data Index: 4286532 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2279. Min Range: -6.2279
Max Act: 5.8529. Min Act: -0.1700
Data Index: 5491144 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2279. Min Range: -6.2279
Max Act: 5.8216. Min Act: -0.1700
Data Index: 4306176 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2279. Min Range: -6.2279
Max Act: 5.8529. Min Act: -0.1700
Data Index: 4162033 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2279. Min Range: -6.2279
Max Act: 5.8216. Min Act: -0.1700
Data Index: 8217903 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19