Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5082 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.4043. Min Range: -1.4043
Max Act: 1.4043. Min Act: -0.1700
Data Index: 5817686 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4043. Min Range: -1.4043
Max Act: 1.3691. Min Act: -0.1700
Data Index: 694072 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4043. Min Range: -1.4043
Max Act: 1.3338. Min Act: -0.1700
Data Index: 7293766 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4043. Min Range: -1.4043
Max Act: 1.3338. Min Act: -0.1700
Data Index: 6355553 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4043. Min Range: -1.4043
Max Act: 1.3162. Min Act: -0.1700
Data Index: 7945770 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4043. Min Range: -1.4043
Max Act: 1.3162. Min Act: -0.1700
Data Index: 2178499 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4043. Min Range: -1.4043
Max Act: 1.2985. Min Act: -0.1700
Data Index: 8219820 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4043. Min Range: -1.4043
Max Act: 1.2985. Min Act: -0.1700
Data Index: 860458 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4043. Min Range: -1.4043
Max Act: 1.2809. Min Act: -0.1700
Data Index: 8387599 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4043. Min Range: -1.4043
Max Act: 1.2632. Min Act: -0.1700
Data Index: 8380641 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4043. Min Range: -1.4043
Max Act: 1.2809. Min Act: -0.1700
Data Index: 2940820 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4043. Min Range: -1.4043
Max Act: 1.2632. Min Act: -0.1700
Data Index: 868219 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4043. Min Range: -1.4043
Max Act: 1.2456. Min Act: -0.1700
Data Index: 3040370 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4043. Min Range: -1.4043
Max Act: 1.2456. Min Act: -0.1700
Data Index: 1995852 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4043. Min Range: -1.4043
Max Act: 1.2456. Min Act: -0.1700
Data Index: 4839852 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4043. Min Range: -1.4043
Max Act: 1.2456. Min Act: -0.1700
Data Index: 6225523 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4043. Min Range: -1.4043
Max Act: 1.2456. Min Act: -0.1700
Data Index: 1041469 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4043. Min Range: -1.4043
Max Act: 1.2280. Min Act: -0.1700
Data Index: 6614916 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4043. Min Range: -1.4043
Max Act: 1.2280. Min Act: -0.1700
Data Index: 4056104 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4043. Min Range: -1.4043
Max Act: 1.2104. Min Act: -0.1700
Data Index: 139800 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #19