Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4948 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7527. Min Range: -6.7527
Max Act: 6.7527. Min Act: -0.1700
Data Index: 4423082 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7527. Min Range: -6.7527
Max Act: 6.7215. Min Act: -0.1700
Data Index: 7190323 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7527. Min Range: -6.7527
Max Act: 6.6902. Min Act: -0.1700
Data Index: 6814331 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7527. Min Range: -6.7527
Max Act: 6.5965. Min Act: -0.1700
Data Index: 7940926 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7527. Min Range: -6.7527
Max Act: 6.5965. Min Act: -0.1700
Data Index: 5009973 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7527. Min Range: -6.7527
Max Act: 6.5027. Min Act: -0.1700
Data Index: 4354409 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7527. Min Range: -6.7527
Max Act: 6.4715. Min Act: -0.1700
Data Index: 7233328 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7527. Min Range: -6.7527
Max Act: 6.5027. Min Act: -0.1700
Data Index: 6135580 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7527. Min Range: -6.7527
Max Act: 6.4715. Min Act: -0.1700
Data Index: 8059521 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7527. Min Range: -6.7527
Max Act: 6.4402. Min Act: -0.1700
Data Index: 4714420 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7527. Min Range: -6.7527
Max Act: 6.3777. Min Act: -0.1700
Data Index: 6257133 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7527. Min Range: -6.7527
Max Act: 6.3777. Min Act: -0.1700
Data Index: 301489 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7527. Min Range: -6.7527
Max Act: 6.3465. Min Act: -0.1700
Data Index: 5624388 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7527. Min Range: -6.7527
Max Act: 6.3152. Min Act: -0.1700
Data Index: 5543615 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7527. Min Range: -6.7527
Max Act: 6.3152. Min Act: -0.1700
Data Index: 8316222 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7527. Min Range: -6.7527
Max Act: 6.2840. Min Act: -0.1700
Data Index: 8159181 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7527. Min Range: -6.7527
Max Act: 6.2840. Min Act: -0.1700
Data Index: 640987 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7527. Min Range: -6.7527
Max Act: 6.2840. Min Act: -0.1700
Data Index: 783654 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7527. Min Range: -6.7527
Max Act: 6.2840. Min Act: -0.1700
Data Index: 5469551 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7527. Min Range: -6.7527
Max Act: 6.2527. Min Act: -0.1700
Data Index: 1120001 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #19