Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6000 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5352. Min Range: -7.5352
Max Act: 7.5352. Min Act: -0.1700
Data Index: 3524395 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5352. Min Range: -7.5352
Max Act: 7.2227. Min Act: -0.1700
Data Index: 111640 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5352. Min Range: -7.5352
Max Act: 7.1915. Min Act: -0.1700
Data Index: 6216633 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5352. Min Range: -7.5352
Max Act: 7.1602. Min Act: -0.1700
Data Index: 2677293 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5352. Min Range: -7.5352
Max Act: 7.1290. Min Act: -0.1700
Data Index: 8161623 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5352. Min Range: -7.5352
Max Act: 7.0665. Min Act: -0.1700
Data Index: 1160581 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5352. Min Range: -7.5352
Max Act: 7.0352. Min Act: -0.1700
Data Index: 5671616 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5352. Min Range: -7.5352
Max Act: 6.9727. Min Act: -0.1700
Data Index: 8310073 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5352. Min Range: -7.5352
Max Act: 6.9727. Min Act: -0.1700
Data Index: 709818 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5352. Min Range: -7.5352
Max Act: 6.9415. Min Act: -0.1700
Data Index: 2045283 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5352. Min Range: -7.5352
Max Act: 6.9102. Min Act: -0.1700
Data Index: 2789454 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5352. Min Range: -7.5352
Max Act: 6.8477. Min Act: -0.1700
Data Index: 7726425 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5352. Min Range: -7.5352
Max Act: 6.8790. Min Act: -0.1700
Data Index: 613597 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5352. Min Range: -7.5352
Max Act: 6.8477. Min Act: -0.1700
Data Index: 709823 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5352. Min Range: -7.5352
Max Act: 6.8165. Min Act: -0.1700
Data Index: 6864550 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5352. Min Range: -7.5352
Max Act: 6.8165. Min Act: -0.1700
Data Index: 4689552 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5352. Min Range: -7.5352
Max Act: 6.8165. Min Act: -0.1700
Data Index: 3918002 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5352. Min Range: -7.5352
Max Act: 6.7852. Min Act: -0.1700
Data Index: 8116254 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5352. Min Range: -7.5352
Max Act: 6.7540. Min Act: -0.1700
Data Index: 6989063 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5352. Min Range: -7.5352
Max Act: 6.7540. Min Act: -0.1700
Data Index: 635203 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #19