Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3089 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6209. Min Range: -3.6209
Max Act: 3.6209. Min Act: -0.1700
Data Index: 1792865 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6209. Min Range: -3.6209
Max Act: 3.5583. Min Act: -0.1700
Data Index: 4952365 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6209. Min Range: -3.6209
Max Act: 3.5583. Min Act: -0.1700
Data Index: 8671122 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6209. Min Range: -3.6209
Max Act: 3.4016. Min Act: -0.1700
Data Index: 6412824 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6209. Min Range: -3.6209
Max Act: 3.4016. Min Act: -0.1700
Data Index: 2815968 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6209. Min Range: -3.6209
Max Act: 3.3860. Min Act: -0.1700
Data Index: 1792849 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6209. Min Range: -3.6209
Max Act: 3.3546. Min Act: -0.1700
Data Index: 4923095 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6209. Min Range: -3.6209
Max Act: 3.3703. Min Act: -0.1700
Data Index: 3016114 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6209. Min Range: -3.6209
Max Act: 3.3232. Min Act: -0.1700
Data Index: 6673852 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6209. Min Range: -3.6209
Max Act: 3.3075. Min Act: -0.1700
Data Index: 7006329 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6209. Min Range: -3.6209
Max Act: 3.2918. Min Act: -0.1700
Data Index: 3702647 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6209. Min Range: -3.6209
Max Act: 3.2918. Min Act: -0.1700
Data Index: 3929445 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6209. Min Range: -3.6209
Max Act: 3.2918. Min Act: -0.1700
Data Index: 6207444 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6209. Min Range: -3.6209
Max Act: 3.2761. Min Act: -0.1700
Data Index: 7585503 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6209. Min Range: -3.6209
Max Act: 3.2918. Min Act: -0.1700
Data Index: 1541411 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6209. Min Range: -3.6209
Max Act: 3.2918. Min Act: -0.1700
Data Index: 2625655 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6209. Min Range: -3.6209
Max Act: 3.2918. Min Act: -0.1700
Data Index: 3181904 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6209. Min Range: -3.6209
Max Act: 3.2447. Min Act: -0.1700
Data Index: 7888177 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6209. Min Range: -3.6209
Max Act: 3.2604. Min Act: -0.1700
Data Index: 8239396 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6209. Min Range: -3.6209
Max Act: 3.2447. Min Act: -0.1700
Data Index: 1276494 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #19