Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6349 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7241. Min Range: -4.7241
Max Act: 4.7241. Min Act: -0.1700
Data Index: 6254974 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7241. Min Range: -4.7241
Max Act: 4.5678. Min Act: -0.1700
Data Index: 8097312 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7241. Min Range: -4.7241
Max Act: 4.3803. Min Act: -0.1700
Data Index: 2793174 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7241. Min Range: -4.7241
Max Act: 4.3490. Min Act: -0.1700
Data Index: 5387022 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7241. Min Range: -4.7241
Max Act: 4.3178. Min Act: -0.1700
Data Index: 4098410 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7241. Min Range: -4.7241
Max Act: 4.3178. Min Act: -0.1700
Data Index: 6663548 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7241. Min Range: -4.7241
Max Act: 4.3178. Min Act: -0.1700
Data Index: 6907524 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7241. Min Range: -4.7241
Max Act: 4.2865. Min Act: -0.1700
Data Index: 5014264 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7241. Min Range: -4.7241
Max Act: 4.2865. Min Act: -0.1700
Data Index: 5025302 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7241. Min Range: -4.7241
Max Act: 4.2240. Min Act: -0.1700
Data Index: 597769 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7241. Min Range: -4.7241
Max Act: 4.1928. Min Act: -0.1700
Data Index: 107625 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7241. Min Range: -4.7241
Max Act: 4.1928. Min Act: -0.1700
Data Index: 6953974 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7241. Min Range: -4.7241
Max Act: 4.2240. Min Act: -0.1700
Data Index: 1609542 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7241. Min Range: -4.7241
Max Act: 4.1615. Min Act: -0.1700
Data Index: 685364 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7241. Min Range: -4.7241
Max Act: 4.1303. Min Act: -0.1700
Data Index: 5826843 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7241. Min Range: -4.7241
Max Act: 4.1615. Min Act: -0.1700
Data Index: 4624933 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7241. Min Range: -4.7241
Max Act: 4.1615. Min Act: -0.1700
Data Index: 1173608 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7241. Min Range: -4.7241
Max Act: 4.1928. Min Act: -0.1700
Data Index: 6166089 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7241. Min Range: -4.7241
Max Act: 4.1615. Min Act: -0.1700
Data Index: 1094728 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7241. Min Range: -4.7241
Max Act: 4.1303. Min Act: -0.1700
Data Index: 4076038 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19