Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3258 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5974. Min Range: -7.5974
Max Act: 7.5974. Min Act: -0.1700
Data Index: 2301721 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5974. Min Range: -7.5974
Max Act: 7.4412. Min Act: -0.1700
Data Index: 1555775 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5974. Min Range: -7.5974
Max Act: 7.4412. Min Act: -0.1700
Data Index: 3160469 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5974. Min Range: -7.5974
Max Act: 7.3162. Min Act: -0.1700
Data Index: 2134897 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5974. Min Range: -7.5974
Max Act: 7.2224. Min Act: -0.1700
Data Index: 5776706 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5974. Min Range: -7.5974
Max Act: 7.2224. Min Act: -0.1700
Data Index: 8506711 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5974. Min Range: -7.5974
Max Act: 7.1912. Min Act: -0.1700
Data Index: 6783457 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5974. Min Range: -7.5974
Max Act: 7.1287. Min Act: -0.1700
Data Index: 6804160 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5974. Min Range: -7.5974
Max Act: 7.1287. Min Act: -0.1700
Data Index: 304844 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5974. Min Range: -7.5974
Max Act: 7.1287. Min Act: -0.1700
Data Index: 1344774 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5974. Min Range: -7.5974
Max Act: 7.0662. Min Act: -0.1700
Data Index: 1543278 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5974. Min Range: -7.5974
Max Act: 7.0349. Min Act: -0.1700
Data Index: 4483072 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5974. Min Range: -7.5974
Max Act: 7.0349. Min Act: -0.1700
Data Index: 5938552 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5974. Min Range: -7.5974
Max Act: 7.0349. Min Act: -0.1700
Data Index: 5951234 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5974. Min Range: -7.5974
Max Act: 7.0349. Min Act: -0.1700
Data Index: 452563 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5974. Min Range: -7.5974
Max Act: 7.0037. Min Act: -0.1700
Data Index: 255863 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5974. Min Range: -7.5974
Max Act: 7.0037. Min Act: -0.1700
Data Index: 6509230 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5974. Min Range: -7.5974
Max Act: 7.0037. Min Act: -0.1700
Data Index: 7805175 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5974. Min Range: -7.5974
Max Act: 7.0037. Min Act: -0.1700
Data Index: 908258 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5974. Min Range: -7.5974
Max Act: 7.0037. Min Act: -0.1700
Data Index: 7404252 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #19