Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3548 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9698. Min Range: -9.9698
Max Act: 9.9698. Min Act: -0.1700
Data Index: 721074 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9698. Min Range: -9.9698
Max Act: 9.7823. Min Act: -0.1700
Data Index: 5002768 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9698. Min Range: -9.9698
Max Act: 9.6573. Min Act: -0.1700
Data Index: 2115203 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9698. Min Range: -9.9698
Max Act: 9.5948. Min Act: -0.1700
Data Index: 541477 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9698. Min Range: -9.9698
Max Act: 9.4698. Min Act: -0.1700
Data Index: 2703263 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9698. Min Range: -9.9698
Max Act: 9.4698. Min Act: -0.1700
Data Index: 3986797 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9698. Min Range: -9.9698
Max Act: 9.3448. Min Act: -0.1700
Data Index: 4486798 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9698. Min Range: -9.9698
Max Act: 9.1573. Min Act: -0.1700
Data Index: 2448650 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9698. Min Range: -9.9698
Max Act: 9.1573. Min Act: -0.1700
Data Index: 5937170 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9698. Min Range: -9.9698
Max Act: 9.1573. Min Act: -0.1700
Data Index: 3417477 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9698. Min Range: -9.9698
Max Act: 9.1573. Min Act: -0.1700
Data Index: 7445744 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9698. Min Range: -9.9698
Max Act: 9.1573. Min Act: -0.1700
Data Index: 4701395 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9698. Min Range: -9.9698
Max Act: 9.1573. Min Act: -0.1700
Data Index: 3876216 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9698. Min Range: -9.9698
Max Act: 9.0948. Min Act: -0.1700
Data Index: 3008656 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9698. Min Range: -9.9698
Max Act: 9.0948. Min Act: -0.1700
Data Index: 1545541 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9698. Min Range: -9.9698
Max Act: 9.0323. Min Act: -0.1700
Data Index: 1702440 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9698. Min Range: -9.9698
Max Act: 9.0323. Min Act: -0.1700
Data Index: 6686953 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9698. Min Range: -9.9698
Max Act: 9.0323. Min Act: -0.1700
Data Index: 8105451 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9698. Min Range: -9.9698
Max Act: 8.9073. Min Act: -0.1700
Data Index: 1113272 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9698. Min Range: -9.9698
Max Act: 9.0323. Min Act: -0.1700
Data Index: 3527681 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19