Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3035 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2326. Min Range: -6.2326
Max Act: 6.2326. Min Act: -0.1700
Data Index: 7411733 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2326. Min Range: -6.2326
Max Act: 5.8264. Min Act: -0.1700
Data Index: 8077104 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2326. Min Range: -6.2326
Max Act: 5.8264. Min Act: -0.1700
Data Index: 4325337 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2326. Min Range: -6.2326
Max Act: 5.7951. Min Act: -0.1700
Data Index: 8392133 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2326. Min Range: -6.2326
Max Act: 5.7639. Min Act: -0.1700
Data Index: 2570224 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2326. Min Range: -6.2326
Max Act: 5.7326. Min Act: -0.1700
Data Index: 7673904 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2326. Min Range: -6.2326
Max Act: 5.7014. Min Act: -0.1700
Data Index: 8189601 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2326. Min Range: -6.2326
Max Act: 5.6389. Min Act: -0.1700
Data Index: 5108626 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2326. Min Range: -6.2326
Max Act: 5.6076. Min Act: -0.1700
Data Index: 7301416 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2326. Min Range: -6.2326
Max Act: 5.6076. Min Act: -0.1700
Data Index: 2258621 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2326. Min Range: -6.2326
Max Act: 5.6701. Min Act: -0.1700
Data Index: 8000447 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2326. Min Range: -6.2326
Max Act: 5.6076. Min Act: -0.1700
Data Index: 761039 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2326. Min Range: -6.2326
Max Act: 5.6076. Min Act: -0.1700
Data Index: 4536216 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2326. Min Range: -6.2326
Max Act: 5.6076. Min Act: -0.1700
Data Index: 4285010 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2326. Min Range: -6.2326
Max Act: 5.5451. Min Act: -0.1700
Data Index: 608014 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2326. Min Range: -6.2326
Max Act: 5.5139. Min Act: -0.1700
Data Index: 3097851 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2326. Min Range: -6.2326
Max Act: 5.5451. Min Act: -0.1700
Data Index: 5899585 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2326. Min Range: -6.2326
Max Act: 5.5451. Min Act: -0.1700
Data Index: 2459986 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2326. Min Range: -6.2326
Max Act: 5.5451. Min Act: -0.1700
Data Index: 3312426 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2326. Min Range: -6.2326
Max Act: 5.5139. Min Act: -0.1700
Data Index: 3720536 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #19