Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1978 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9336. Min Range: -5.9336
Max Act: 5.9336. Min Act: -0.1700
Data Index: 6680420 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9336. Min Range: -5.9336
Max Act: 5.9024. Min Act: -0.1700
Data Index: 5998824 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9336. Min Range: -5.9336
Max Act: 5.9336. Min Act: -0.1700
Data Index: 2858506 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9336. Min Range: -5.9336
Max Act: 5.8086. Min Act: -0.1700
Data Index: 1957431 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9336. Min Range: -5.9336
Max Act: 5.8399. Min Act: -0.1700
Data Index: 344208 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9336. Min Range: -5.9336
Max Act: 5.7461. Min Act: -0.1700
Data Index: 3263038 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9336. Min Range: -5.9336
Max Act: 5.7461. Min Act: -0.1700
Data Index: 3664829 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9336. Min Range: -5.9336
Max Act: 5.7149. Min Act: -0.1700
Data Index: 694991 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9336. Min Range: -5.9336
Max Act: 5.6211. Min Act: -0.1700
Data Index: 4862890 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9336. Min Range: -5.9336
Max Act: 5.6524. Min Act: -0.1700
Data Index: 7327193 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9336. Min Range: -5.9336
Max Act: 5.6524. Min Act: -0.1700
Data Index: 2844396 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9336. Min Range: -5.9336
Max Act: 5.6211. Min Act: -0.1700
Data Index: 1875885 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9336. Min Range: -5.9336
Max Act: 5.6211. Min Act: -0.1700
Data Index: 6840068 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9336. Min Range: -5.9336
Max Act: 5.5899. Min Act: -0.1700
Data Index: 860856 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9336. Min Range: -5.9336
Max Act: 5.6211. Min Act: -0.1700
Data Index: 5573379 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9336. Min Range: -5.9336
Max Act: 5.6211. Min Act: -0.1700
Data Index: 1462728 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9336. Min Range: -5.9336
Max Act: 5.6211. Min Act: -0.1700
Data Index: 8042861 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9336. Min Range: -5.9336
Max Act: 5.6211. Min Act: -0.1700
Data Index: 4586101 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9336. Min Range: -5.9336
Max Act: 5.5899. Min Act: -0.1700
Data Index: 2505586 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9336. Min Range: -5.9336
Max Act: 5.5899. Min Act: -0.1700
Data Index: 8482589 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #19