Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 496 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.4540. Min Range: -8.4540
Max Act: 8.4540. Min Act: -0.1700
Data Index: 610630 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4540. Min Range: -8.4540
Max Act: 8.4540. Min Act: -0.1700
Data Index: 3446233 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4540. Min Range: -8.4540
Max Act: 8.3290. Min Act: -0.1700
Data Index: 1934061 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4540. Min Range: -8.4540
Max Act: 8.3290. Min Act: -0.1700
Data Index: 1257056 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4540. Min Range: -8.4540
Max Act: 8.2665. Min Act: -0.1700
Data Index: 8165791 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4540. Min Range: -8.4540
Max Act: 8.2040. Min Act: -0.1700
Data Index: 2726062 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4540. Min Range: -8.4540
Max Act: 8.1415. Min Act: -0.1700
Data Index: 5343127 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4540. Min Range: -8.4540
Max Act: 8.1415. Min Act: -0.1700
Data Index: 4157737 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4540. Min Range: -8.4540
Max Act: 8.0790. Min Act: -0.1700
Data Index: 3431468 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4540. Min Range: -8.4540
Max Act: 8.0165. Min Act: -0.1700
Data Index: 7340430 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4540. Min Range: -8.4540
Max Act: 8.0165. Min Act: -0.1700
Data Index: 1384595 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4540. Min Range: -8.4540
Max Act: 8.0790. Min Act: -0.1700
Data Index: 1166976 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4540. Min Range: -8.4540
Max Act: 8.0165. Min Act: -0.1700
Data Index: 7171209 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4540. Min Range: -8.4540
Max Act: 8.0165. Min Act: -0.1700
Data Index: 2188044 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4540. Min Range: -8.4540
Max Act: 7.9540. Min Act: -0.1700
Data Index: 2184749 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4540. Min Range: -8.4540
Max Act: 8.0790. Min Act: -0.1700
Data Index: 3073285 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4540. Min Range: -8.4540
Max Act: 7.9540. Min Act: -0.1700
Data Index: 3541628 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4540. Min Range: -8.4540
Max Act: 7.9540. Min Act: -0.1700
Data Index: 193139 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4540. Min Range: -8.4540
Max Act: 7.9540. Min Act: -0.1700
Data Index: 8130719 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4540. Min Range: -8.4540
Max Act: 7.8915. Min Act: -0.1700
Data Index: 5419065 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #19