Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6397 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6382. Min Range: -7.6382
Max Act: 7.6382. Min Act: -0.1700
Data Index: 6981060 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6382. Min Range: -7.6382
Max Act: 7.3882. Min Act: -0.1700
Data Index: 4758422 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6382. Min Range: -7.6382
Max Act: 7.2007. Min Act: -0.1700
Data Index: 5336922 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6382. Min Range: -7.6382
Max Act: 7.1070. Min Act: -0.1700
Data Index: 6209402 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6382. Min Range: -7.6382
Max Act: 7.1382. Min Act: -0.1700
Data Index: 1657505 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6382. Min Range: -7.6382
Max Act: 7.1382. Min Act: -0.1700
Data Index: 1479978 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6382. Min Range: -7.6382
Max Act: 6.9195. Min Act: -0.1700
Data Index: 1757770 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6382. Min Range: -7.6382
Max Act: 6.9507. Min Act: -0.1700
Data Index: 7789416 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6382. Min Range: -7.6382
Max Act: 6.9507. Min Act: -0.1700
Data Index: 8611040 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6382. Min Range: -7.6382
Max Act: 6.9195. Min Act: -0.1700
Data Index: 40467 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6382. Min Range: -7.6382
Max Act: 6.9195. Min Act: -0.1700
Data Index: 1090465 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6382. Min Range: -7.6382
Max Act: 6.9195. Min Act: -0.1700
Data Index: 2147239 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6382. Min Range: -7.6382
Max Act: 6.9195. Min Act: -0.1700
Data Index: 7122313 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6382. Min Range: -7.6382
Max Act: 6.8882. Min Act: -0.1700
Data Index: 6540323 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6382. Min Range: -7.6382
Max Act: 6.8570. Min Act: -0.1700
Data Index: 6926196 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6382. Min Range: -7.6382
Max Act: 6.8570. Min Act: -0.1700
Data Index: 3210028 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6382. Min Range: -7.6382
Max Act: 6.8570. Min Act: -0.1700
Data Index: 3704327 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6382. Min Range: -7.6382
Max Act: 6.8570. Min Act: -0.1700
Data Index: 413623 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6382. Min Range: -7.6382
Max Act: 6.8570. Min Act: -0.1700
Data Index: 1381088 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6382. Min Range: -7.6382
Max Act: 6.7945. Min Act: -0.1700
Data Index: 5460348 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #19