Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1953 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4843. Min Range: -5.4843
Max Act: 5.4843. Min Act: -0.1700
Data Index: 6534123 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4843. Min Range: -5.4843
Max Act: 5.4218. Min Act: -0.1700
Data Index: 8815682 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4843. Min Range: -5.4843
Max Act: 5.3593. Min Act: -0.1700
Data Index: 6760213 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4843. Min Range: -5.4843
Max Act: 5.3593. Min Act: -0.1700
Data Index: 6083173 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4843. Min Range: -5.4843
Max Act: 5.3281. Min Act: -0.1700
Data Index: 8209428 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4843. Min Range: -5.4843
Max Act: 5.3281. Min Act: -0.1700
Data Index: 138548 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4843. Min Range: -5.4843
Max Act: 5.2968. Min Act: -0.1700
Data Index: 6680696 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4843. Min Range: -5.4843
Max Act: 5.2968. Min Act: -0.1700
Data Index: 8115477 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4843. Min Range: -5.4843
Max Act: 5.2968. Min Act: -0.1700
Data Index: 3825989 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4843. Min Range: -5.4843
Max Act: 5.2968. Min Act: -0.1700
Data Index: 1394004 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4843. Min Range: -5.4843
Max Act: 5.2968. Min Act: -0.1700
Data Index: 6431671 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4843. Min Range: -5.4843
Max Act: 5.2656. Min Act: -0.1700
Data Index: 6802849 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4843. Min Range: -5.4843
Max Act: 5.2656. Min Act: -0.1700
Data Index: 1493668 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4843. Min Range: -5.4843
Max Act: 5.2343. Min Act: -0.1700
Data Index: 6628143 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4843. Min Range: -5.4843
Max Act: 5.2343. Min Act: -0.1700
Data Index: 868179 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4843. Min Range: -5.4843
Max Act: 5.2031. Min Act: -0.1700
Data Index: 7502570 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4843. Min Range: -5.4843
Max Act: 5.2343. Min Act: -0.1700
Data Index: 37688 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4843. Min Range: -5.4843
Max Act: 5.2031. Min Act: -0.1700
Data Index: 5583520 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4843. Min Range: -5.4843
Max Act: 5.2031. Min Act: -0.1700
Data Index: 535322 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4843. Min Range: -5.4843
Max Act: 5.2031. Min Act: -0.1700
Data Index: 4992366 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19