Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2564 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.0778. Min Range: -8.0778
Max Act: 8.0778. Min Act: -0.1700
Data Index: 3876870 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0778. Min Range: -8.0778
Max Act: 7.9528. Min Act: -0.1700
Data Index: 1819221 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0778. Min Range: -8.0778
Max Act: 7.8278. Min Act: -0.1700
Data Index: 2961599 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0778. Min Range: -8.0778
Max Act: 7.7965. Min Act: -0.1700
Data Index: 8141776 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0778. Min Range: -8.0778
Max Act: 7.7653. Min Act: -0.1700
Data Index: 381631 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0778. Min Range: -8.0778
Max Act: 7.7653. Min Act: -0.1700
Data Index: 5418613 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0778. Min Range: -8.0778
Max Act: 7.6715. Min Act: -0.1700
Data Index: 3731504 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0778. Min Range: -8.0778
Max Act: 7.6090. Min Act: -0.1700
Data Index: 8345876 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0778. Min Range: -8.0778
Max Act: 7.6090. Min Act: -0.1700
Data Index: 1215620 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0778. Min Range: -8.0778
Max Act: 7.5778. Min Act: -0.1700
Data Index: 2081735 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0778. Min Range: -8.0778
Max Act: 7.5465. Min Act: -0.1700
Data Index: 5159468 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0778. Min Range: -8.0778
Max Act: 7.5778. Min Act: -0.1700
Data Index: 2464464 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0778. Min Range: -8.0778
Max Act: 7.5465. Min Act: -0.1700
Data Index: 4927540 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0778. Min Range: -8.0778
Max Act: 7.5465. Min Act: -0.1700
Data Index: 7341014 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0778. Min Range: -8.0778
Max Act: 7.5153. Min Act: -0.1700
Data Index: 3756535 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0778. Min Range: -8.0778
Max Act: 7.4840. Min Act: -0.1700
Data Index: 865068 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0778. Min Range: -8.0778
Max Act: 7.4840. Min Act: -0.1700
Data Index: 4180301 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0778. Min Range: -8.0778
Max Act: 7.5153. Min Act: -0.1700
Data Index: 4070483 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0778. Min Range: -8.0778
Max Act: 7.5153. Min Act: -0.1700
Data Index: 4895508 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0778. Min Range: -8.0778
Max Act: 7.4840. Min Act: -0.1700
Data Index: 1816544 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #19