Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3604 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0303. Min Range: -6.0303
Max Act: 6.0303. Min Act: -0.1700
Data Index: 4380914 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0303. Min Range: -6.0303
Max Act: 5.9053. Min Act: -0.1700
Data Index: 8559272 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0303. Min Range: -6.0303
Max Act: 5.8740. Min Act: -0.1700
Data Index: 4450307 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0303. Min Range: -6.0303
Max Act: 5.8428. Min Act: -0.1700
Data Index: 2127051 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0303. Min Range: -6.0303
Max Act: 5.8428. Min Act: -0.1700
Data Index: 6616946 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0303. Min Range: -6.0303
Max Act: 5.7490. Min Act: -0.1700
Data Index: 1516203 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0303. Min Range: -6.0303
Max Act: 5.7803. Min Act: -0.1700
Data Index: 1480742 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0303. Min Range: -6.0303
Max Act: 5.8115. Min Act: -0.1700
Data Index: 11263 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0303. Min Range: -6.0303
Max Act: 5.7178. Min Act: -0.1700
Data Index: 4715422 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0303. Min Range: -6.0303
Max Act: 5.7178. Min Act: -0.1700
Data Index: 3664486 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0303. Min Range: -6.0303
Max Act: 5.7178. Min Act: -0.1700
Data Index: 2037510 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0303. Min Range: -6.0303
Max Act: 5.6865. Min Act: -0.1700
Data Index: 7002823 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0303. Min Range: -6.0303
Max Act: 5.6865. Min Act: -0.1700
Data Index: 8550970 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0303. Min Range: -6.0303
Max Act: 5.6865. Min Act: -0.1700
Data Index: 1988203 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0303. Min Range: -6.0303
Max Act: 5.6553. Min Act: -0.1700
Data Index: 1240084 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0303. Min Range: -6.0303
Max Act: 5.6240. Min Act: -0.1700
Data Index: 6481415 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0303. Min Range: -6.0303
Max Act: 5.6553. Min Act: -0.1700
Data Index: 8037509 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0303. Min Range: -6.0303
Max Act: 5.6240. Min Act: -0.1700
Data Index: 1958735 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0303. Min Range: -6.0303
Max Act: 5.6240. Min Act: -0.1700
Data Index: 4472568 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0303. Min Range: -6.0303
Max Act: 5.6240. Min Act: -0.1700
Data Index: 6824089 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19