Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3412 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0171. Min Range: -8.0171
Max Act: 8.0171. Min Act: -0.1700
Data Index: 6050887 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0171. Min Range: -8.0171
Max Act: 7.9546. Min Act: -0.1700
Data Index: 1287443 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0171. Min Range: -8.0171
Max Act: 7.9546. Min Act: -0.1700
Data Index: 7336462 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0171. Min Range: -8.0171
Max Act: 7.8921. Min Act: -0.1700
Data Index: 6468257 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0171. Min Range: -8.0171
Max Act: 7.7671. Min Act: -0.1700
Data Index: 1207692 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0171. Min Range: -8.0171
Max Act: 7.7671. Min Act: -0.1700
Data Index: 376210 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0171. Min Range: -8.0171
Max Act: 7.6109. Min Act: -0.1700
Data Index: 8688407 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0171. Min Range: -8.0171
Max Act: 7.5796. Min Act: -0.1700
Data Index: 4252405 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0171. Min Range: -8.0171
Max Act: 7.5484. Min Act: -0.1700
Data Index: 8698967 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0171. Min Range: -8.0171
Max Act: 7.5171. Min Act: -0.1700
Data Index: 2999708 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0171. Min Range: -8.0171
Max Act: 7.5171. Min Act: -0.1700
Data Index: 4339530 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0171. Min Range: -8.0171
Max Act: 7.5171. Min Act: -0.1700
Data Index: 2547330 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0171. Min Range: -8.0171
Max Act: 7.4859. Min Act: -0.1700
Data Index: 8777539 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0171. Min Range: -8.0171
Max Act: 7.4859. Min Act: -0.1700
Data Index: 4895930 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0171. Min Range: -8.0171
Max Act: 7.4546. Min Act: -0.1700
Data Index: 4300320 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0171. Min Range: -8.0171
Max Act: 7.4546. Min Act: -0.1700
Data Index: 6323453 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0171. Min Range: -8.0171
Max Act: 7.4546. Min Act: -0.1700
Data Index: 3962128 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0171. Min Range: -8.0171
Max Act: 7.4546. Min Act: -0.1700
Data Index: 6041456 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0171. Min Range: -8.0171
Max Act: 7.4234. Min Act: -0.1700
Data Index: 3428707 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0171. Min Range: -8.0171
Max Act: 7.4234. Min Act: -0.1700
Data Index: 4300321 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19