Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1236 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.4213. Min Range: -11.4213
Max Act: 11.4213. Min Act: -0.1700
Data Index: 3506367 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.4213. Min Range: -11.4213
Max Act: 10.8588. Min Act: -0.1700
Data Index: 8501399 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.4213. Min Range: -11.4213
Max Act: 10.7338. Min Act: -0.1700
Data Index: 1359245 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.4213. Min Range: -11.4213
Max Act: 10.6713. Min Act: -0.1700
Data Index: 1695962 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.4213. Min Range: -11.4213
Max Act: 10.4213. Min Act: -0.1700
Data Index: 7760179 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.4213. Min Range: -11.4213
Max Act: 10.0463. Min Act: -0.1700
Data Index: 4996986 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.4213. Min Range: -11.4213
Max Act: 9.8588. Min Act: -0.1700
Data Index: 4996987 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.4213. Min Range: -11.4213
Max Act: 9.9213. Min Act: -0.1700
Data Index: 5345045 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.4213. Min Range: -11.4213
Max Act: 9.8588. Min Act: -0.1700
Data Index: 2533156 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.4213. Min Range: -11.4213
Max Act: 9.7963. Min Act: -0.1700
Data Index: 2135872 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.4213. Min Range: -11.4213
Max Act: 9.7963. Min Act: -0.1700
Data Index: 4680915 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.4213. Min Range: -11.4213
Max Act: 9.7963. Min Act: -0.1700
Data Index: 5624637 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.4213. Min Range: -11.4213
Max Act: 9.7963. Min Act: -0.1700
Data Index: 2351021 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.4213. Min Range: -11.4213
Max Act: 9.7963. Min Act: -0.1700
Data Index: 6370477 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.4213. Min Range: -11.4213
Max Act: 9.7338. Min Act: -0.1700
Data Index: 2031520 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.4213. Min Range: -11.4213
Max Act: 9.7338. Min Act: -0.1700
Data Index: 103921 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.4213. Min Range: -11.4213
Max Act: 9.7338. Min Act: -0.1700
Data Index: 1559901 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.4213. Min Range: -11.4213
Max Act: 9.6088. Min Act: -0.1700
Data Index: 5345046 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.4213. Min Range: -11.4213
Max Act: 9.6713. Min Act: -0.1700
Data Index: 4400420 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.4213. Min Range: -11.4213
Max Act: 9.6713. Min Act: -0.1700
Data Index: 4468690 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #19