Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3435 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1036. Min Range: -6.1036
Max Act: 6.1036. Min Act: -0.1700
Data Index: 5916742 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1036. Min Range: -6.1036
Max Act: 6.0411. Min Act: -0.1700
Data Index: 3945560 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1036. Min Range: -6.1036
Max Act: 5.9786. Min Act: -0.1700
Data Index: 7639522 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1036. Min Range: -6.1036
Max Act: 5.9474. Min Act: -0.1700
Data Index: 4366993 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1036. Min Range: -6.1036
Max Act: 5.9161. Min Act: -0.1700
Data Index: 39908 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1036. Min Range: -6.1036
Max Act: 5.9161. Min Act: -0.1700
Data Index: 3636636 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1036. Min Range: -6.1036
Max Act: 5.8849. Min Act: -0.1700
Data Index: 7639523 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1036. Min Range: -6.1036
Max Act: 5.8849. Min Act: -0.1700
Data Index: 2337212 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1036. Min Range: -6.1036
Max Act: 5.8536. Min Act: -0.1700
Data Index: 6646674 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1036. Min Range: -6.1036
Max Act: 5.8536. Min Act: -0.1700
Data Index: 3636637 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1036. Min Range: -6.1036
Max Act: 5.8224. Min Act: -0.1700
Data Index: 2337223 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1036. Min Range: -6.1036
Max Act: 5.8224. Min Act: -0.1700
Data Index: 8580204 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1036. Min Range: -6.1036
Max Act: 5.7911. Min Act: -0.1700
Data Index: 6999609 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1036. Min Range: -6.1036
Max Act: 5.7599. Min Act: -0.1700
Data Index: 1059121 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1036. Min Range: -6.1036
Max Act: 5.6974. Min Act: -0.1700
Data Index: 3945563 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1036. Min Range: -6.1036
Max Act: 5.7286. Min Act: -0.1700
Data Index: 3945564 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1036. Min Range: -6.1036
Max Act: 5.7286. Min Act: -0.1700
Data Index: 6331862 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1036. Min Range: -6.1036
Max Act: 5.6974. Min Act: -0.1700
Data Index: 6116345 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1036. Min Range: -6.1036
Max Act: 5.6661. Min Act: -0.1700
Data Index: 6121134 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1036. Min Range: -6.1036
Max Act: 5.6974. Min Act: -0.1700
Data Index: 7046567 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #19