Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 551 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7417. Min Range: -5.7417
Max Act: 5.7417. Min Act: -0.1700
Data Index: 8188625 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7417. Min Range: -5.7417
Max Act: 5.6480. Min Act: -0.1700
Data Index: 7668046 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7417. Min Range: -5.7417
Max Act: 5.5855. Min Act: -0.1700
Data Index: 2217314 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7417. Min Range: -5.7417
Max Act: 5.5542. Min Act: -0.1700
Data Index: 3275154 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7417. Min Range: -5.7417
Max Act: 5.4917. Min Act: -0.1700
Data Index: 831119 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7417. Min Range: -5.7417
Max Act: 5.4605. Min Act: -0.1700
Data Index: 4288749 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7417. Min Range: -5.7417
Max Act: 5.4605. Min Act: -0.1700
Data Index: 6504662 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7417. Min Range: -5.7417
Max Act: 5.4292. Min Act: -0.1700
Data Index: 4669688 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7417. Min Range: -5.7417
Max Act: 5.3980. Min Act: -0.1700
Data Index: 7645628 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7417. Min Range: -5.7417
Max Act: 5.3667. Min Act: -0.1700
Data Index: 1284778 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7417. Min Range: -5.7417
Max Act: 5.3980. Min Act: -0.1700
Data Index: 4459164 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7417. Min Range: -5.7417
Max Act: 5.3667. Min Act: -0.1700
Data Index: 8675637 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7417. Min Range: -5.7417
Max Act: 5.3355. Min Act: -0.1700
Data Index: 921603 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7417. Min Range: -5.7417
Max Act: 5.3355. Min Act: -0.1700
Data Index: 512547 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7417. Min Range: -5.7417
Max Act: 5.3355. Min Act: -0.1700
Data Index: 4212320 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7417. Min Range: -5.7417
Max Act: 5.2730. Min Act: -0.1700
Data Index: 6375995 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7417. Min Range: -5.7417
Max Act: 5.2730. Min Act: -0.1700
Data Index: 1091353 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7417. Min Range: -5.7417
Max Act: 5.3355. Min Act: -0.1700
Data Index: 2810966 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7417. Min Range: -5.7417
Max Act: 5.2730. Min Act: -0.1700
Data Index: 2106980 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7417. Min Range: -5.7417
Max Act: 5.2730. Min Act: -0.1700
Data Index: 6350286 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #19