Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4240 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.6999. Min Range: -8.6999
Max Act: 8.6999. Min Act: -0.1700
Data Index: 5962087 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6999. Min Range: -8.6999
Max Act: 8.6999. Min Act: -0.1700
Data Index: 5993319 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6999. Min Range: -8.6999
Max Act: 8.6374. Min Act: -0.1700
Data Index: 5343908 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6999. Min Range: -8.6999
Max Act: 8.5124. Min Act: -0.1700
Data Index: 1525645 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6999. Min Range: -8.6999
Max Act: 8.3874. Min Act: -0.1700
Data Index: 5523603 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6999. Min Range: -8.6999
Max Act: 8.3249. Min Act: -0.1700
Data Index: 2237314 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6999. Min Range: -8.6999
Max Act: 8.2624. Min Act: -0.1700
Data Index: 1702654 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6999. Min Range: -8.6999
Max Act: 8.2311. Min Act: -0.1700
Data Index: 4695401 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6999. Min Range: -8.6999
Max Act: 8.2311. Min Act: -0.1700
Data Index: 2433504 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6999. Min Range: -8.6999
Max Act: 8.1999. Min Act: -0.1700
Data Index: 2251439 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6999. Min Range: -8.6999
Max Act: 8.1686. Min Act: -0.1700
Data Index: 5997225 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6999. Min Range: -8.6999
Max Act: 8.1061. Min Act: -0.1700
Data Index: 2808513 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6999. Min Range: -8.6999
Max Act: 8.0749. Min Act: -0.1700
Data Index: 1173631 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6999. Min Range: -8.6999
Max Act: 8.1061. Min Act: -0.1700
Data Index: 4710202 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6999. Min Range: -8.6999
Max Act: 8.0749. Min Act: -0.1700
Data Index: 939651 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6999. Min Range: -8.6999
Max Act: 8.0749. Min Act: -0.1700
Data Index: 1104836 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6999. Min Range: -8.6999
Max Act: 8.0749. Min Act: -0.1700
Data Index: 4592171 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6999. Min Range: -8.6999
Max Act: 8.0749. Min Act: -0.1700
Data Index: 2219172 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6999. Min Range: -8.6999
Max Act: 8.0436. Min Act: -0.1700
Data Index: 1377722 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6999. Min Range: -8.6999
Max Act: 8.0436. Min Act: -0.1700
Data Index: 8201327 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #19