Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3806 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6402. Min Range: -9.6402
Max Act: 9.6402. Min Act: -0.1700
Data Index: 4616467 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6402. Min Range: -9.6402
Max Act: 9.5152. Min Act: -0.1700
Data Index: 446685 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6402. Min Range: -9.6402
Max Act: 9.3902. Min Act: -0.1700
Data Index: 8184841 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6402. Min Range: -9.6402
Max Act: 9.3902. Min Act: -0.1700
Data Index: 1015839 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6402. Min Range: -9.6402
Max Act: 9.3277. Min Act: -0.1700
Data Index: 6231932 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6402. Min Range: -9.6402
Max Act: 9.3277. Min Act: -0.1700
Data Index: 2554160 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6402. Min Range: -9.6402
Max Act: 9.3277. Min Act: -0.1700
Data Index: 4643046 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6402. Min Range: -9.6402
Max Act: 9.2027. Min Act: -0.1700
Data Index: 925488 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6402. Min Range: -9.6402
Max Act: 9.0777. Min Act: -0.1700
Data Index: 3462692 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6402. Min Range: -9.6402
Max Act: 9.0777. Min Act: -0.1700
Data Index: 5756019 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6402. Min Range: -9.6402
Max Act: 9.0152. Min Act: -0.1700
Data Index: 7980757 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6402. Min Range: -9.6402
Max Act: 8.9527. Min Act: -0.1700
Data Index: 2083453 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6402. Min Range: -9.6402
Max Act: 8.9527. Min Act: -0.1700
Data Index: 5307829 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6402. Min Range: -9.6402
Max Act: 8.9527. Min Act: -0.1700
Data Index: 5238919 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6402. Min Range: -9.6402
Max Act: 8.9527. Min Act: -0.1700
Data Index: 2622669 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6402. Min Range: -9.6402
Max Act: 8.8902. Min Act: -0.1700
Data Index: 6520060 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6402. Min Range: -9.6402
Max Act: 8.8902. Min Act: -0.1700
Data Index: 2842768 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6402. Min Range: -9.6402
Max Act: 8.8902. Min Act: -0.1700
Data Index: 2674345 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6402. Min Range: -9.6402
Max Act: 8.8277. Min Act: -0.1700
Data Index: 8635704 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6402. Min Range: -9.6402
Max Act: 8.8902. Min Act: -0.1700
Data Index: 966768 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19