Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3486 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7090. Min Range: -6.7090
Max Act: 6.7090. Min Act: -0.1700
Data Index: 745591 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7090. Min Range: -6.7090
Max Act: 6.6152. Min Act: -0.1700
Data Index: 8267268 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7090. Min Range: -6.7090
Max Act: 6.5840. Min Act: -0.1700
Data Index: 5659946 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7090. Min Range: -6.7090
Max Act: 6.5215. Min Act: -0.1700
Data Index: 8289717 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7090. Min Range: -6.7090
Max Act: 6.3965. Min Act: -0.1700
Data Index: 8499808 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7090. Min Range: -6.7090
Max Act: 6.3652. Min Act: -0.1700
Data Index: 864783 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7090. Min Range: -6.7090
Max Act: 6.2715. Min Act: -0.1700
Data Index: 7654591 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7090. Min Range: -6.7090
Max Act: 6.2715. Min Act: -0.1700
Data Index: 3084741 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7090. Min Range: -6.7090
Max Act: 6.2402. Min Act: -0.1700
Data Index: 8724300 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7090. Min Range: -6.7090
Max Act: 6.1777. Min Act: -0.1700
Data Index: 6327797 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7090. Min Range: -6.7090
Max Act: 6.1777. Min Act: -0.1700
Data Index: 4590573 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7090. Min Range: -6.7090
Max Act: 6.0840. Min Act: -0.1700
Data Index: 3995812 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7090. Min Range: -6.7090
Max Act: 6.1152. Min Act: -0.1700
Data Index: 5677065 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7090. Min Range: -6.7090
Max Act: 6.1152. Min Act: -0.1700
Data Index: 480192 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7090. Min Range: -6.7090
Max Act: 6.1152. Min Act: -0.1700
Data Index: 4570461 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7090. Min Range: -6.7090
Max Act: 6.0840. Min Act: -0.1700
Data Index: 123969 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7090. Min Range: -6.7090
Max Act: 6.0840. Min Act: -0.1700
Data Index: 930149 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7090. Min Range: -6.7090
Max Act: 6.0527. Min Act: -0.1700
Data Index: 672244 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7090. Min Range: -6.7090
Max Act: 6.0840. Min Act: -0.1700
Data Index: 4947297 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7090. Min Range: -6.7090
Max Act: 6.0215. Min Act: -0.1700
Data Index: 1438735 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #19