Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2942 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.5233. Min Range: -8.5233
Max Act: 8.5233. Min Act: -0.1700
Data Index: 7460247 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5233. Min Range: -8.5233
Max Act: 7.8983. Min Act: -0.1700
Data Index: 5044798 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5233. Min Range: -8.5233
Max Act: 7.8045. Min Act: -0.1700
Data Index: 4536627 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5233. Min Range: -8.5233
Max Act: 7.6795. Min Act: -0.1700
Data Index: 4393283 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5233. Min Range: -8.5233
Max Act: 7.5858. Min Act: -0.1700
Data Index: 4287469 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5233. Min Range: -8.5233
Max Act: 7.5233. Min Act: -0.1700
Data Index: 2381970 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5233. Min Range: -8.5233
Max Act: 7.4920. Min Act: -0.1700
Data Index: 1742974 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5233. Min Range: -8.5233
Max Act: 7.4608. Min Act: -0.1700
Data Index: 3568690 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5233. Min Range: -8.5233
Max Act: 7.4295. Min Act: -0.1700
Data Index: 3708087 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5233. Min Range: -8.5233
Max Act: 7.4295. Min Act: -0.1700
Data Index: 3642606 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5233. Min Range: -8.5233
Max Act: 7.3983. Min Act: -0.1700
Data Index: 4536645 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5233. Min Range: -8.5233
Max Act: 7.3045. Min Act: -0.1700
Data Index: 2323580 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5233. Min Range: -8.5233
Max Act: 7.2420. Min Act: -0.1700
Data Index: 8780658 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5233. Min Range: -8.5233
Max Act: 7.2108. Min Act: -0.1700
Data Index: 5739909 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5233. Min Range: -8.5233
Max Act: 7.1170. Min Act: -0.1700
Data Index: 2125510 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5233. Min Range: -8.5233
Max Act: 7.1170. Min Act: -0.1700
Data Index: 5692614 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5233. Min Range: -8.5233
Max Act: 7.1170. Min Act: -0.1700
Data Index: 7275028 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5233. Min Range: -8.5233
Max Act: 7.0858. Min Act: -0.1700
Data Index: 4375286 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5233. Min Range: -8.5233
Max Act: 7.0858. Min Act: -0.1700
Data Index: 4450753 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5233. Min Range: -8.5233
Max Act: 7.1170. Min Act: -0.1700
Data Index: 2971626 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #19