Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 660 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6096. Min Range: -6.6096
Max Act: 6.6096. Min Act: -0.1700
Data Index: 31089 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6096. Min Range: -6.6096
Max Act: 6.5158. Min Act: -0.1700
Data Index: 1564572 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6096. Min Range: -6.6096
Max Act: 6.5471. Min Act: -0.1700
Data Index: 917677 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6096. Min Range: -6.6096
Max Act: 6.4533. Min Act: -0.1700
Data Index: 8039940 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6096. Min Range: -6.6096
Max Act: 6.3283. Min Act: -0.1700
Data Index: 8045419 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6096. Min Range: -6.6096
Max Act: 6.3283. Min Act: -0.1700
Data Index: 5033151 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6096. Min Range: -6.6096
Max Act: 6.3283. Min Act: -0.1700
Data Index: 2140136 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6096. Min Range: -6.6096
Max Act: 6.2033. Min Act: -0.1700
Data Index: 2664129 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6096. Min Range: -6.6096
Max Act: 6.2033. Min Act: -0.1700
Data Index: 7807452 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6096. Min Range: -6.6096
Max Act: 6.2033. Min Act: -0.1700
Data Index: 330113 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6096. Min Range: -6.6096
Max Act: 6.1408. Min Act: -0.1700
Data Index: 3820873 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6096. Min Range: -6.6096
Max Act: 6.1096. Min Act: -0.1700
Data Index: 5139267 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6096. Min Range: -6.6096
Max Act: 6.1096. Min Act: -0.1700
Data Index: 7147979 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6096. Min Range: -6.6096
Max Act: 6.0471. Min Act: -0.1700
Data Index: 6334488 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6096. Min Range: -6.6096
Max Act: 6.0783. Min Act: -0.1700
Data Index: 5445124 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6096. Min Range: -6.6096
Max Act: 6.0471. Min Act: -0.1700
Data Index: 6294757 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6096. Min Range: -6.6096
Max Act: 6.0471. Min Act: -0.1700
Data Index: 7956670 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6096. Min Range: -6.6096
Max Act: 6.0471. Min Act: -0.1700
Data Index: 3221381 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6096. Min Range: -6.6096
Max Act: 6.0158. Min Act: -0.1700
Data Index: 3365890 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6096. Min Range: -6.6096
Max Act: 6.0158. Min Act: -0.1700
Data Index: 8549503 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19