Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 691 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7343. Min Range: -5.7343
Max Act: 5.7343. Min Act: -0.1700
Data Index: 3598897 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7343. Min Range: -5.7343
Max Act: 5.5781. Min Act: -0.1700
Data Index: 5766853 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7343. Min Range: -5.7343
Max Act: 5.5156. Min Act: -0.1700
Data Index: 6647582 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7343. Min Range: -5.7343
Max Act: 5.4843. Min Act: -0.1700
Data Index: 5766855 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7343. Min Range: -5.7343
Max Act: 5.4531. Min Act: -0.1700
Data Index: 8392237 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7343. Min Range: -5.7343
Max Act: 5.4218. Min Act: -0.1700
Data Index: 6957110 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7343. Min Range: -5.7343
Max Act: 5.3593. Min Act: -0.1700
Data Index: 5766852 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7343. Min Range: -5.7343
Max Act: 5.3281. Min Act: -0.1700
Data Index: 39679 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7343. Min Range: -5.7343
Max Act: 5.3593. Min Act: -0.1700
Data Index: 6635233 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7343. Min Range: -5.7343
Max Act: 5.3281. Min Act: -0.1700
Data Index: 7935854 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7343. Min Range: -5.7343
Max Act: 5.2968. Min Act: -0.1700
Data Index: 7646718 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7343. Min Range: -5.7343
Max Act: 5.2968. Min Act: -0.1700
Data Index: 8201183 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7343. Min Range: -5.7343
Max Act: 5.2968. Min Act: -0.1700
Data Index: 6647584 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7343. Min Range: -5.7343
Max Act: 5.2968. Min Act: -0.1700
Data Index: 4815219 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7343. Min Range: -5.7343
Max Act: 5.2968. Min Act: -0.1700
Data Index: 6656503 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7343. Min Range: -5.7343
Max Act: 5.2656. Min Act: -0.1700
Data Index: 4512213 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7343. Min Range: -5.7343
Max Act: 5.2656. Min Act: -0.1700
Data Index: 3655156 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7343. Min Range: -5.7343
Max Act: 5.2343. Min Act: -0.1700
Data Index: 6232355 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7343. Min Range: -5.7343
Max Act: 5.2656. Min Act: -0.1700
Data Index: 7653703 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7343. Min Range: -5.7343
Max Act: 5.2343. Min Act: -0.1700
Data Index: 107146 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19