Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2655 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7084. Min Range: -3.7084
Max Act: 3.7084. Min Act: -0.1700
Data Index: 5697585 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7084. Min Range: -3.7084
Max Act: 3.6928. Min Act: -0.1700
Data Index: 637452 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7084. Min Range: -3.7084
Max Act: 3.6928. Min Act: -0.1700
Data Index: 2714202 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7084. Min Range: -3.7084
Max Act: 3.6615. Min Act: -0.1700
Data Index: 6222118 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7084. Min Range: -3.7084
Max Act: 3.6615. Min Act: -0.1700
Data Index: 2394198 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7084. Min Range: -3.7084
Max Act: 3.6615. Min Act: -0.1700
Data Index: 5283135 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7084. Min Range: -3.7084
Max Act: 3.6615. Min Act: -0.1700
Data Index: 1378385 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7084. Min Range: -3.7084
Max Act: 3.6458. Min Act: -0.1700
Data Index: 3796852 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7084. Min Range: -3.7084
Max Act: 3.6302. Min Act: -0.1700
Data Index: 3306968 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7084. Min Range: -3.7084
Max Act: 3.6145. Min Act: -0.1700
Data Index: 8507941 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7084. Min Range: -3.7084
Max Act: 3.6458. Min Act: -0.1700
Data Index: 7379908 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7084. Min Range: -3.7084
Max Act: 3.6302. Min Act: -0.1700
Data Index: 1995964 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7084. Min Range: -3.7084
Max Act: 3.6145. Min Act: -0.1700
Data Index: 8326642 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7084. Min Range: -3.7084
Max Act: 3.6145. Min Act: -0.1700
Data Index: 567676 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7084. Min Range: -3.7084
Max Act: 3.5989. Min Act: -0.1700
Data Index: 7075404 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7084. Min Range: -3.7084
Max Act: 3.6302. Min Act: -0.1700
Data Index: 2474030 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7084. Min Range: -3.7084
Max Act: 3.6145. Min Act: -0.1700
Data Index: 6868329 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7084. Min Range: -3.7084
Max Act: 3.5989. Min Act: -0.1700
Data Index: 6517984 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7084. Min Range: -3.7084
Max Act: 3.6145. Min Act: -0.1700
Data Index: 1581307 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7084. Min Range: -3.7084
Max Act: 3.5989. Min Act: -0.1700
Data Index: 6311215 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19