Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2598 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5620. Min Range: -4.5620
Max Act: 4.5620. Min Act: -0.1700
Data Index: 5549458 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5620. Min Range: -4.5620
Max Act: 4.4370. Min Act: -0.1700
Data Index: 7498565 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5620. Min Range: -4.5620
Max Act: 4.4057. Min Act: -0.1700
Data Index: 5229992 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5620. Min Range: -4.5620
Max Act: 4.4057. Min Act: -0.1700
Data Index: 8573961 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5620. Min Range: -4.5620
Max Act: 4.3432. Min Act: -0.1700
Data Index: 7872088 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5620. Min Range: -4.5620
Max Act: 4.3120. Min Act: -0.1700
Data Index: 1277914 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5620. Min Range: -4.5620
Max Act: 4.3120. Min Act: -0.1700
Data Index: 418792 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5620. Min Range: -4.5620
Max Act: 4.3120. Min Act: -0.1700
Data Index: 4361627 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5620. Min Range: -4.5620
Max Act: 4.3120. Min Act: -0.1700
Data Index: 8446093 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5620. Min Range: -4.5620
Max Act: 4.3120. Min Act: -0.1700
Data Index: 1442572 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5620. Min Range: -4.5620
Max Act: 4.2807. Min Act: -0.1700
Data Index: 5335054 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5620. Min Range: -4.5620
Max Act: 4.2807. Min Act: -0.1700
Data Index: 8091876 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5620. Min Range: -4.5620
Max Act: 4.2807. Min Act: -0.1700
Data Index: 5657354 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5620. Min Range: -4.5620
Max Act: 4.2807. Min Act: -0.1700
Data Index: 4287109 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5620. Min Range: -4.5620
Max Act: 4.2495. Min Act: -0.1700
Data Index: 5772194 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5620. Min Range: -4.5620
Max Act: 4.2495. Min Act: -0.1700
Data Index: 5229555 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5620. Min Range: -4.5620
Max Act: 4.2495. Min Act: -0.1700
Data Index: 903499 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5620. Min Range: -4.5620
Max Act: 4.2182. Min Act: -0.1700
Data Index: 233664 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5620. Min Range: -4.5620
Max Act: 4.2182. Min Act: -0.1700
Data Index: 4891227 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5620. Min Range: -4.5620
Max Act: 4.2182. Min Act: -0.1700
Data Index: 5004113 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19