Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 143 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9343. Min Range: -5.9343
Max Act: 5.9343. Min Act: -0.1700
Data Index: 6251125 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9343. Min Range: -5.9343
Max Act: 5.9343. Min Act: -0.1700
Data Index: 7661733 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9343. Min Range: -5.9343
Max Act: 5.9030. Min Act: -0.1700
Data Index: 4173350 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9343. Min Range: -5.9343
Max Act: 5.8718. Min Act: -0.1700
Data Index: 2931969 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9343. Min Range: -5.9343
Max Act: 5.8718. Min Act: -0.1700
Data Index: 2455794 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9343. Min Range: -5.9343
Max Act: 5.8093. Min Act: -0.1700
Data Index: 8814798 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9343. Min Range: -5.9343
Max Act: 5.8405. Min Act: -0.1700
Data Index: 2250650 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9343. Min Range: -5.9343
Max Act: 5.7780. Min Act: -0.1700
Data Index: 2197775 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9343. Min Range: -5.9343
Max Act: 5.8093. Min Act: -0.1700
Data Index: 2477093 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9343. Min Range: -5.9343
Max Act: 5.8093. Min Act: -0.1700
Data Index: 5400835 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9343. Min Range: -5.9343
Max Act: 5.8093. Min Act: -0.1700
Data Index: 6655141 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9343. Min Range: -5.9343
Max Act: 5.7468. Min Act: -0.1700
Data Index: 767165 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9343. Min Range: -5.9343
Max Act: 5.7780. Min Act: -0.1700
Data Index: 1200192 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9343. Min Range: -5.9343
Max Act: 5.7780. Min Act: -0.1700
Data Index: 8209265 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9343. Min Range: -5.9343
Max Act: 5.7780. Min Act: -0.1700
Data Index: 1164353 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9343. Min Range: -5.9343
Max Act: 5.7780. Min Act: -0.1700
Data Index: 1688310 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9343. Min Range: -5.9343
Max Act: 5.8093. Min Act: -0.1700
Data Index: 5291297 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9343. Min Range: -5.9343
Max Act: 5.7780. Min Act: -0.1700
Data Index: 7008389 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9343. Min Range: -5.9343
Max Act: 5.7468. Min Act: -0.1700
Data Index: 4449565 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9343. Min Range: -5.9343
Max Act: 5.7468. Min Act: -0.1700
Data Index: 4037774 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19