Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5578 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1773. Min Range: -5.1773
Max Act: 5.1461. Min Act: -0.1700
Data Index: 7953540 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1773. Min Range: -5.1773
Max Act: 5.1461. Min Act: -0.1700
Data Index: 6009455 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1773. Min Range: -5.1773
Max Act: 5.1461. Min Act: -0.1700
Data Index: 8544118 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1773. Min Range: -5.1773
Max Act: 5.1773. Min Act: -0.1700
Data Index: 5221796 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1773. Min Range: -5.1773
Max Act: 5.1148. Min Act: -0.1700
Data Index: 914777 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1773. Min Range: -5.1773
Max Act: 5.1148. Min Act: -0.1700
Data Index: 4069254 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1773. Min Range: -5.1773
Max Act: 5.1148. Min Act: -0.1700
Data Index: 5879847 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1773. Min Range: -5.1773
Max Act: 5.0836. Min Act: -0.1700
Data Index: 3010099 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1773. Min Range: -5.1773
Max Act: 5.0836. Min Act: -0.1700
Data Index: 4308921 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1773. Min Range: -5.1773
Max Act: 5.1148. Min Act: -0.1700
Data Index: 4261070 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1773. Min Range: -5.1773
Max Act: 5.0836. Min Act: -0.1700
Data Index: 6946327 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1773. Min Range: -5.1773
Max Act: 5.0836. Min Act: -0.1700
Data Index: 6972831 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1773. Min Range: -5.1773
Max Act: 5.0836. Min Act: -0.1700
Data Index: 4490537 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1773. Min Range: -5.1773
Max Act: 5.0836. Min Act: -0.1700
Data Index: 5321713 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1773. Min Range: -5.1773
Max Act: 5.0836. Min Act: -0.1700
Data Index: 4492166 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1773. Min Range: -5.1773
Max Act: 5.0836. Min Act: -0.1700
Data Index: 2821321 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1773. Min Range: -5.1773
Max Act: 5.0523. Min Act: -0.1700
Data Index: 5775700 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1773. Min Range: -5.1773
Max Act: 5.0523. Min Act: -0.1700
Data Index: 6121865 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1773. Min Range: -5.1773
Max Act: 5.0523. Min Act: -0.1700
Data Index: 8330796 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1773. Min Range: -5.1773
Max Act: 5.0523. Min Act: -0.1700
Data Index: 2884204 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #19