Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1058 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4277. Min Range: -6.4277
Max Act: 6.4277. Min Act: -0.1700
Data Index: 5049924 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4277. Min Range: -6.4277
Max Act: 6.3652. Min Act: -0.1700
Data Index: 1772366 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4277. Min Range: -6.4277
Max Act: 6.3339. Min Act: -0.1700
Data Index: 735972 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4277. Min Range: -6.4277
Max Act: 6.2714. Min Act: -0.1700
Data Index: 4232197 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4277. Min Range: -6.4277
Max Act: 6.2714. Min Act: -0.1700
Data Index: 5085812 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4277. Min Range: -6.4277
Max Act: 6.1464. Min Act: -0.1700
Data Index: 7300073 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4277. Min Range: -6.4277
Max Act: 6.1152. Min Act: -0.1700
Data Index: 5128338 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4277. Min Range: -6.4277
Max Act: 6.1152. Min Act: -0.1700
Data Index: 1681581 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4277. Min Range: -6.4277
Max Act: 6.0839. Min Act: -0.1700
Data Index: 1090975 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4277. Min Range: -6.4277
Max Act: 6.0527. Min Act: -0.1700
Data Index: 4914641 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4277. Min Range: -6.4277
Max Act: 6.0527. Min Act: -0.1700
Data Index: 5288878 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4277. Min Range: -6.4277
Max Act: 6.0214. Min Act: -0.1700
Data Index: 6312532 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4277. Min Range: -6.4277
Max Act: 6.0214. Min Act: -0.1700
Data Index: 5648783 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4277. Min Range: -6.4277
Max Act: 6.0214. Min Act: -0.1700
Data Index: 2229028 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4277. Min Range: -6.4277
Max Act: 5.9902. Min Act: -0.1700
Data Index: 6976215 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4277. Min Range: -6.4277
Max Act: 5.9902. Min Act: -0.1700
Data Index: 210628 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4277. Min Range: -6.4277
Max Act: 5.9902. Min Act: -0.1700
Data Index: 7007015 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4277. Min Range: -6.4277
Max Act: 5.9589. Min Act: -0.1700
Data Index: 7235666 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4277. Min Range: -6.4277
Max Act: 6.0214. Min Act: -0.1700
Data Index: 5407582 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4277. Min Range: -6.4277
Max Act: 5.9902. Min Act: -0.1700
Data Index: 976373 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #19