Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1035 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3873. Min Range: -7.3873
Max Act: 7.3873. Min Act: -0.1700
Data Index: 3457986 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3873. Min Range: -7.3873
Max Act: 7.3248. Min Act: -0.1700
Data Index: 3457987 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3873. Min Range: -7.3873
Max Act: 7.1060. Min Act: -0.1700
Data Index: 234838 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3873. Min Range: -7.3873
Max Act: 7.0435. Min Act: -0.1700
Data Index: 3457982 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3873. Min Range: -7.3873
Max Act: 6.9810. Min Act: -0.1700
Data Index: 7490600 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3873. Min Range: -7.3873
Max Act: 6.9185. Min Act: -0.1700
Data Index: 701481 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3873. Min Range: -7.3873
Max Act: 6.7935. Min Act: -0.1700
Data Index: 5068227 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3873. Min Range: -7.3873
Max Act: 6.7310. Min Act: -0.1700
Data Index: 3195875 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3873. Min Range: -7.3873
Max Act: 6.7310. Min Act: -0.1700
Data Index: 2627862 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3873. Min Range: -7.3873
Max Act: 6.7623. Min Act: -0.1700
Data Index: 5047189 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3873. Min Range: -7.3873
Max Act: 6.7310. Min Act: -0.1700
Data Index: 830316 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3873. Min Range: -7.3873
Max Act: 6.7310. Min Act: -0.1700
Data Index: 6722959 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3873. Min Range: -7.3873
Max Act: 6.6685. Min Act: -0.1700
Data Index: 6948984 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3873. Min Range: -7.3873
Max Act: 6.6060. Min Act: -0.1700
Data Index: 1591643 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3873. Min Range: -7.3873
Max Act: 6.5748. Min Act: -0.1700
Data Index: 8830529 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3873. Min Range: -7.3873
Max Act: 6.5435. Min Act: -0.1700
Data Index: 701475 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3873. Min Range: -7.3873
Max Act: 6.5748. Min Act: -0.1700
Data Index: 4330317 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3873. Min Range: -7.3873
Max Act: 6.5123. Min Act: -0.1700
Data Index: 7491395 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3873. Min Range: -7.3873
Max Act: 6.4810. Min Act: -0.1700
Data Index: 8733881 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3873. Min Range: -7.3873
Max Act: 6.4498. Min Act: -0.1700
Data Index: 712326 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #19