Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 329 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.9834. Min Range: -8.9834
Max Act: 8.9834. Min Act: -0.1700
Data Index: 2834540 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9834. Min Range: -8.9834
Max Act: 8.7334. Min Act: -0.1700
Data Index: 8091169 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9834. Min Range: -8.9834
Max Act: 8.6709. Min Act: -0.1700
Data Index: 32397 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9834. Min Range: -8.9834
Max Act: 8.5459. Min Act: -0.1700
Data Index: 2041455 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9834. Min Range: -8.9834
Max Act: 8.4209. Min Act: -0.1700
Data Index: 5400365 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9834. Min Range: -8.9834
Max Act: 8.4209. Min Act: -0.1700
Data Index: 530263 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9834. Min Range: -8.9834
Max Act: 8.4209. Min Act: -0.1700
Data Index: 4524089 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9834. Min Range: -8.9834
Max Act: 8.3584. Min Act: -0.1700
Data Index: 7715531 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9834. Min Range: -8.9834
Max Act: 8.2334. Min Act: -0.1700
Data Index: 4151874 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9834. Min Range: -8.9834
Max Act: 8.1397. Min Act: -0.1700
Data Index: 5041728 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9834. Min Range: -8.9834
Max Act: 8.2334. Min Act: -0.1700
Data Index: 7201517 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9834. Min Range: -8.9834
Max Act: 8.1709. Min Act: -0.1700
Data Index: 3863620 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9834. Min Range: -8.9834
Max Act: 8.1709. Min Act: -0.1700
Data Index: 3948330 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9834. Min Range: -8.9834
Max Act: 8.1397. Min Act: -0.1700
Data Index: 8174128 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9834. Min Range: -8.9834
Max Act: 8.1397. Min Act: -0.1700
Data Index: 4302876 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9834. Min Range: -8.9834
Max Act: 8.1709. Min Act: -0.1700
Data Index: 7840801 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9834. Min Range: -8.9834
Max Act: 8.1397. Min Act: -0.1700
Data Index: 1121284 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9834. Min Range: -8.9834
Max Act: 8.1084. Min Act: -0.1700
Data Index: 3840418 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9834. Min Range: -8.9834
Max Act: 8.0459. Min Act: -0.1700
Data Index: 1116157 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9834. Min Range: -8.9834
Max Act: 8.0459. Min Act: -0.1700
Data Index: 6800468 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #19