Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1968 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.5639. Min Range: -7.5639
Max Act: 7.5639. Min Act: -0.1700
Data Index: 4237879 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5639. Min Range: -7.5639
Max Act: 7.5639. Min Act: -0.1700
Data Index: 7926580 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5639. Min Range: -7.5639
Max Act: 7.4389. Min Act: -0.1700
Data Index: 4780312 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5639. Min Range: -7.5639
Max Act: 7.2201. Min Act: -0.1700
Data Index: 4970752 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5639. Min Range: -7.5639
Max Act: 7.1576. Min Act: -0.1700
Data Index: 7926561 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5639. Min Range: -7.5639
Max Act: 7.1264. Min Act: -0.1700
Data Index: 581371 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5639. Min Range: -7.5639
Max Act: 7.0326. Min Act: -0.1700
Data Index: 6149383 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5639. Min Range: -7.5639
Max Act: 7.0014. Min Act: -0.1700
Data Index: 3466943 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5639. Min Range: -7.5639
Max Act: 6.9701. Min Act: -0.1700
Data Index: 7093699 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5639. Min Range: -7.5639
Max Act: 6.9076. Min Act: -0.1700
Data Index: 7394504 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5639. Min Range: -7.5639
Max Act: 6.8764. Min Act: -0.1700
Data Index: 1578529 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5639. Min Range: -7.5639
Max Act: 6.8451. Min Act: -0.1700
Data Index: 623388 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5639. Min Range: -7.5639
Max Act: 6.8139. Min Act: -0.1700
Data Index: 4104884 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5639. Min Range: -7.5639
Max Act: 6.8451. Min Act: -0.1700
Data Index: 1393612 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5639. Min Range: -7.5639
Max Act: 6.8139. Min Act: -0.1700
Data Index: 387578 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5639. Min Range: -7.5639
Max Act: 6.7826. Min Act: -0.1700
Data Index: 4477734 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5639. Min Range: -7.5639
Max Act: 6.7826. Min Act: -0.1700
Data Index: 1545154 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5639. Min Range: -7.5639
Max Act: 6.7826. Min Act: -0.1700
Data Index: 6976277 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5639. Min Range: -7.5639
Max Act: 6.7514. Min Act: -0.1700
Data Index: 3272132 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5639. Min Range: -7.5639
Max Act: 6.7514. Min Act: -0.1700
Data Index: 689941 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #19