Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5243 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5074. Min Range: -3.5074
Max Act: 3.5074. Min Act: -0.1700
Data Index: 3006084 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5074. Min Range: -3.5074
Max Act: 3.3977. Min Act: -0.1700
Data Index: 2557005 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5074. Min Range: -3.5074
Max Act: 3.3663. Min Act: -0.1700
Data Index: 6631246 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5074. Min Range: -3.5074
Max Act: 3.3506. Min Act: -0.1700
Data Index: 5850074 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5074. Min Range: -3.5074
Max Act: 3.3036. Min Act: -0.1700
Data Index: 2149204 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5074. Min Range: -3.5074
Max Act: 3.2879. Min Act: -0.1700
Data Index: 5463387 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5074. Min Range: -3.5074
Max Act: 3.2565. Min Act: -0.1700
Data Index: 71992 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5074. Min Range: -3.5074
Max Act: 3.2565. Min Act: -0.1700
Data Index: 577993 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5074. Min Range: -3.5074
Max Act: 3.2250. Min Act: -0.1700
Data Index: 4501495 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5074. Min Range: -3.5074
Max Act: 3.2250. Min Act: -0.1700
Data Index: 2426039 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5074. Min Range: -3.5074
Max Act: 3.2250. Min Act: -0.1700
Data Index: 236367 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5074. Min Range: -3.5074
Max Act: 3.2250. Min Act: -0.1700
Data Index: 1068169 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5074. Min Range: -3.5074
Max Act: 3.2093. Min Act: -0.1700
Data Index: 4733940 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5074. Min Range: -3.5074
Max Act: 3.1936. Min Act: -0.1700
Data Index: 1304111 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5074. Min Range: -3.5074
Max Act: 3.1779. Min Act: -0.1700
Data Index: 7336456 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5074. Min Range: -3.5074
Max Act: 3.2093. Min Act: -0.1700
Data Index: 4242049 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5074. Min Range: -3.5074
Max Act: 3.1779. Min Act: -0.1700
Data Index: 756576 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5074. Min Range: -3.5074
Max Act: 3.1621. Min Act: -0.1700
Data Index: 3309141 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5074. Min Range: -3.5074
Max Act: 3.1779. Min Act: -0.1700
Data Index: 472701 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5074. Min Range: -3.5074
Max Act: 3.1621. Min Act: -0.1700
Data Index: 85610 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19