Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 553 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7819. Min Range: -5.7819
Max Act: 5.7819. Min Act: -0.1700
Data Index: 7091227 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7819. Min Range: -5.7819
Max Act: 5.7506. Min Act: -0.1700
Data Index: 3409989 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7819. Min Range: -5.7819
Max Act: 5.7194. Min Act: -0.1700
Data Index: 2986942 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7819. Min Range: -5.7819
Max Act: 5.6881. Min Act: -0.1700
Data Index: 7012324 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7819. Min Range: -5.7819
Max Act: 5.6569. Min Act: -0.1700
Data Index: 5283443 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7819. Min Range: -5.7819
Max Act: 5.6256. Min Act: -0.1700
Data Index: 8512291 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7819. Min Range: -5.7819
Max Act: 5.5319. Min Act: -0.1700
Data Index: 6478700 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7819. Min Range: -5.7819
Max Act: 5.5319. Min Act: -0.1700
Data Index: 99814 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7819. Min Range: -5.7819
Max Act: 5.5006. Min Act: -0.1700
Data Index: 6389092 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7819. Min Range: -5.7819
Max Act: 5.5006. Min Act: -0.1700
Data Index: 8657035 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7819. Min Range: -5.7819
Max Act: 5.4694. Min Act: -0.1700
Data Index: 2284079 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7819. Min Range: -5.7819
Max Act: 5.4694. Min Act: -0.1700
Data Index: 1340370 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7819. Min Range: -5.7819
Max Act: 5.4381. Min Act: -0.1700
Data Index: 8708602 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7819. Min Range: -5.7819
Max Act: 5.4069. Min Act: -0.1700
Data Index: 570390 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7819. Min Range: -5.7819
Max Act: 5.4069. Min Act: -0.1700
Data Index: 5300736 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7819. Min Range: -5.7819
Max Act: 5.4381. Min Act: -0.1700
Data Index: 4273247 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7819. Min Range: -5.7819
Max Act: 5.4069. Min Act: -0.1700
Data Index: 4828925 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7819. Min Range: -5.7819
Max Act: 5.4069. Min Act: -0.1700
Data Index: 5725435 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7819. Min Range: -5.7819
Max Act: 5.4069. Min Act: -0.1700
Data Index: 2225257 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7819. Min Range: -5.7819
Max Act: 5.4069. Min Act: -0.1700
Data Index: 6225484 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #19