Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 81 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.9663. Min Range: -11.9663
Max Act: 11.9038. Min Act: -0.1700
Data Index: 3251354 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.9663. Min Range: -11.9663
Max Act: 11.9663. Min Act: -0.1700
Data Index: 2510756 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.9663. Min Range: -11.9663
Max Act: 11.7788. Min Act: -0.1700
Data Index: 8239334 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.9663. Min Range: -11.9663
Max Act: 11.6538. Min Act: -0.1700
Data Index: 1065026 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.9663. Min Range: -11.9663
Max Act: 11.6538. Min Act: -0.1700
Data Index: 5734556 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.9663. Min Range: -11.9663
Max Act: 11.5913. Min Act: -0.1700
Data Index: 6644895 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.9663. Min Range: -11.9663
Max Act: 11.5288. Min Act: -0.1700
Data Index: 6048255 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.9663. Min Range: -11.9663
Max Act: 11.4038. Min Act: -0.1700
Data Index: 5645891 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.9663. Min Range: -11.9663
Max Act: 11.4038. Min Act: -0.1700
Data Index: 1219378 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.9663. Min Range: -11.9663
Max Act: 11.3413. Min Act: -0.1700
Data Index: 4578221 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.9663. Min Range: -11.9663
Max Act: 11.2788. Min Act: -0.1700
Data Index: 2979994 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.9663. Min Range: -11.9663
Max Act: 11.2788. Min Act: -0.1700
Data Index: 5025835 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.9663. Min Range: -11.9663
Max Act: 11.2788. Min Act: -0.1700
Data Index: 4375784 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.9663. Min Range: -11.9663
Max Act: 11.2788. Min Act: -0.1700
Data Index: 3872963 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.9663. Min Range: -11.9663
Max Act: 11.2788. Min Act: -0.1700
Data Index: 7831875 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.9663. Min Range: -11.9663
Max Act: 11.2788. Min Act: -0.1700
Data Index: 6776253 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.9663. Min Range: -11.9663
Max Act: 11.2788. Min Act: -0.1700
Data Index: 2692130 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.9663. Min Range: -11.9663
Max Act: 11.2788. Min Act: -0.1700
Data Index: 7756597 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.9663. Min Range: -11.9663
Max Act: 11.2163. Min Act: -0.1700
Data Index: 802971 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.9663. Min Range: -11.9663
Max Act: 11.2163. Min Act: -0.1700
Data Index: 8639580 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19