Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3000 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0171. Min Range: -7.0171
Max Act: 7.0171. Min Act: -0.1700
Data Index: 1872077 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0171. Min Range: -7.0171
Max Act: 6.8921. Min Act: -0.1700
Data Index: 5824177 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0171. Min Range: -7.0171
Max Act: 6.8296. Min Act: -0.1700
Data Index: 3483501 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0171. Min Range: -7.0171
Max Act: 6.8296. Min Act: -0.1700
Data Index: 3100929 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0171. Min Range: -7.0171
Max Act: 6.7359. Min Act: -0.1700
Data Index: 1207379 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0171. Min Range: -7.0171
Max Act: 6.7671. Min Act: -0.1700
Data Index: 2767494 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0171. Min Range: -7.0171
Max Act: 6.6109. Min Act: -0.1700
Data Index: 3503684 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0171. Min Range: -7.0171
Max Act: 6.6734. Min Act: -0.1700
Data Index: 1955412 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0171. Min Range: -7.0171
Max Act: 6.5796. Min Act: -0.1700
Data Index: 7028825 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0171. Min Range: -7.0171
Max Act: 6.6109. Min Act: -0.1700
Data Index: 275654 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0171. Min Range: -7.0171
Max Act: 6.5484. Min Act: -0.1700
Data Index: 8606057 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0171. Min Range: -7.0171
Max Act: 6.5484. Min Act: -0.1700
Data Index: 1180740 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0171. Min Range: -7.0171
Max Act: 6.4546. Min Act: -0.1700
Data Index: 2080816 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0171. Min Range: -7.0171
Max Act: 6.4234. Min Act: -0.1700
Data Index: 867082 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0171. Min Range: -7.0171
Max Act: 6.3921. Min Act: -0.1700
Data Index: 4364108 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0171. Min Range: -7.0171
Max Act: 6.3609. Min Act: -0.1700
Data Index: 1097821 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0171. Min Range: -7.0171
Max Act: 6.3921. Min Act: -0.1700
Data Index: 5261710 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0171. Min Range: -7.0171
Max Act: 6.3921. Min Act: -0.1700
Data Index: 3547239 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0171. Min Range: -7.0171
Max Act: 6.3609. Min Act: -0.1700
Data Index: 3526227 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0171. Min Range: -7.0171
Max Act: 6.3921. Min Act: -0.1700
Data Index: 902957 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19