Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1782 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4411. Min Range: -4.4411
Max Act: 4.4411. Min Act: -0.1700
Data Index: 3265249 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4411. Min Range: -4.4411
Max Act: 4.4411. Min Act: -0.1700
Data Index: 3921013 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4411. Min Range: -4.4411
Max Act: 4.3786. Min Act: -0.1700
Data Index: 5623793 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4411. Min Range: -4.4411
Max Act: 4.3786. Min Act: -0.1700
Data Index: 379605 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4411. Min Range: -4.4411
Max Act: 4.3474. Min Act: -0.1700
Data Index: 5467414 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4411. Min Range: -4.4411
Max Act: 4.4099. Min Act: -0.1700
Data Index: 2280888 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4411. Min Range: -4.4411
Max Act: 4.3474. Min Act: -0.1700
Data Index: 7902615 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4411. Min Range: -4.4411
Max Act: 4.3474. Min Act: -0.1700
Data Index: 4512292 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4411. Min Range: -4.4411
Max Act: 4.3161. Min Act: -0.1700
Data Index: 1663994 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4411. Min Range: -4.4411
Max Act: 4.3786. Min Act: -0.1700
Data Index: 7932195 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4411. Min Range: -4.4411
Max Act: 4.3161. Min Act: -0.1700
Data Index: 8052761 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4411. Min Range: -4.4411
Max Act: 4.3161. Min Act: -0.1700
Data Index: 8497231 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4411. Min Range: -4.4411
Max Act: 4.3161. Min Act: -0.1700
Data Index: 4166591 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4411. Min Range: -4.4411
Max Act: 4.3474. Min Act: -0.1700
Data Index: 7028846 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4411. Min Range: -4.4411
Max Act: 4.3161. Min Act: -0.1700
Data Index: 4697447 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4411. Min Range: -4.4411
Max Act: 4.3474. Min Act: -0.1700
Data Index: 6669764 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4411. Min Range: -4.4411
Max Act: 4.2849. Min Act: -0.1700
Data Index: 7131372 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4411. Min Range: -4.4411
Max Act: 4.2849. Min Act: -0.1700
Data Index: 7394891 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4411. Min Range: -4.4411
Max Act: 4.2849. Min Act: -0.1700
Data Index: 1679968 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4411. Min Range: -4.4411
Max Act: 4.3161. Min Act: -0.1700
Data Index: 5345193 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #19