Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5391 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8381. Min Range: -4.8381
Max Act: 4.8381. Min Act: -0.1700
Data Index: 1712551 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8381. Min Range: -4.8381
Max Act: 4.8069. Min Act: -0.1700
Data Index: 7475478 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8381. Min Range: -4.8381
Max Act: 4.7756. Min Act: -0.1700
Data Index: 5253435 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8381. Min Range: -4.8381
Max Act: 4.7131. Min Act: -0.1700
Data Index: 4059538 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8381. Min Range: -4.8381
Max Act: 4.6819. Min Act: -0.1700
Data Index: 5755218 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8381. Min Range: -4.8381
Max Act: 4.6194. Min Act: -0.1700
Data Index: 3031646 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8381. Min Range: -4.8381
Max Act: 4.6194. Min Act: -0.1700
Data Index: 5877570 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8381. Min Range: -4.8381
Max Act: 4.6194. Min Act: -0.1700
Data Index: 4631439 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8381. Min Range: -4.8381
Max Act: 4.5569. Min Act: -0.1700
Data Index: 7236707 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8381. Min Range: -4.8381
Max Act: 4.5881. Min Act: -0.1700
Data Index: 2379244 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8381. Min Range: -4.8381
Max Act: 4.5881. Min Act: -0.1700
Data Index: 695088 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8381. Min Range: -4.8381
Max Act: 4.5569. Min Act: -0.1700
Data Index: 3172469 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8381. Min Range: -4.8381
Max Act: 4.5569. Min Act: -0.1700
Data Index: 6626671 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8381. Min Range: -4.8381
Max Act: 4.5569. Min Act: -0.1700
Data Index: 954419 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8381. Min Range: -4.8381
Max Act: 4.4944. Min Act: -0.1700
Data Index: 3588029 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8381. Min Range: -4.8381
Max Act: 4.5256. Min Act: -0.1700
Data Index: 4797291 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8381. Min Range: -4.8381
Max Act: 4.5256. Min Act: -0.1700
Data Index: 3679058 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8381. Min Range: -4.8381
Max Act: 4.5256. Min Act: -0.1700
Data Index: 7981854 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8381. Min Range: -4.8381
Max Act: 4.4944. Min Act: -0.1700
Data Index: 4869044 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8381. Min Range: -4.8381
Max Act: 4.4944. Min Act: -0.1700
Data Index: 430864 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19