Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3495 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9336. Min Range: -5.9336
Max Act: 5.9336. Min Act: -0.1700
Data Index: 4617104 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9336. Min Range: -5.9336
Max Act: 5.9024. Min Act: -0.1700
Data Index: 1778005 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9336. Min Range: -5.9336
Max Act: 5.7461. Min Act: -0.1700
Data Index: 2696907 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9336. Min Range: -5.9336
Max Act: 5.7149. Min Act: -0.1700
Data Index: 219963 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9336. Min Range: -5.9336
Max Act: 5.6211. Min Act: -0.1700
Data Index: 1689348 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9336. Min Range: -5.9336
Max Act: 5.5899. Min Act: -0.1700
Data Index: 1273391 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9336. Min Range: -5.9336
Max Act: 5.5899. Min Act: -0.1700
Data Index: 3310554 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9336. Min Range: -5.9336
Max Act: 5.5899. Min Act: -0.1700
Data Index: 1841320 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9336. Min Range: -5.9336
Max Act: 5.5274. Min Act: -0.1700
Data Index: 2855847 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9336. Min Range: -5.9336
Max Act: 5.5274. Min Act: -0.1700
Data Index: 2433755 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9336. Min Range: -5.9336
Max Act: 5.5586. Min Act: -0.1700
Data Index: 3257167 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9336. Min Range: -5.9336
Max Act: 5.4961. Min Act: -0.1700
Data Index: 1270871 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9336. Min Range: -5.9336
Max Act: 5.4336. Min Act: -0.1700
Data Index: 6956595 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9336. Min Range: -5.9336
Max Act: 5.4336. Min Act: -0.1700
Data Index: 5844955 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9336. Min Range: -5.9336
Max Act: 5.4649. Min Act: -0.1700
Data Index: 4214784 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9336. Min Range: -5.9336
Max Act: 5.4024. Min Act: -0.1700
Data Index: 6189966 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9336. Min Range: -5.9336
Max Act: 5.3711. Min Act: -0.1700
Data Index: 615089 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9336. Min Range: -5.9336
Max Act: 5.3711. Min Act: -0.1700
Data Index: 3031894 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9336. Min Range: -5.9336
Max Act: 5.3711. Min Act: -0.1700
Data Index: 3574252 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9336. Min Range: -5.9336
Max Act: 5.3399. Min Act: -0.1700
Data Index: 3449215 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #19