Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4953 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6664. Min Range: -2.6664
Max Act: 2.6664. Min Act: -0.1700
Data Index: 1098960 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6664. Min Range: -2.6664
Max Act: 2.6182. Min Act: -0.1700
Data Index: 8668175 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6664. Min Range: -2.6664
Max Act: 2.5538. Min Act: -0.1700
Data Index: 8219142 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6664. Min Range: -2.6664
Max Act: 2.5376. Min Act: -0.1700
Data Index: 2635501 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6664. Min Range: -2.6664
Max Act: 2.5376. Min Act: -0.1700
Data Index: 588079 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6664. Min Range: -2.6664
Max Act: 2.5214. Min Act: -0.1700
Data Index: 7885492 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6664. Min Range: -2.6664
Max Act: 2.4891. Min Act: -0.1700
Data Index: 5017354 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6664. Min Range: -2.6664
Max Act: 2.5053. Min Act: -0.1700
Data Index: 7455840 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6664. Min Range: -2.6664
Max Act: 2.5053. Min Act: -0.1700
Data Index: 919475 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6664. Min Range: -2.6664
Max Act: 2.4891. Min Act: -0.1700
Data Index: 5750009 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6664. Min Range: -2.6664
Max Act: 2.4891. Min Act: -0.1700
Data Index: 3378346 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6664. Min Range: -2.6664
Max Act: 2.4728. Min Act: -0.1700
Data Index: 4486023 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6664. Min Range: -2.6664
Max Act: 2.4728. Min Act: -0.1700
Data Index: 1486802 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6664. Min Range: -2.6664
Max Act: 2.4566. Min Act: -0.1700
Data Index: 7216989 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6664. Min Range: -2.6664
Max Act: 2.4566. Min Act: -0.1700
Data Index: 1781200 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6664. Min Range: -2.6664
Max Act: 2.4728. Min Act: -0.1700
Data Index: 6824616 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6664. Min Range: -2.6664
Max Act: 2.4403. Min Act: -0.1700
Data Index: 5047765 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6664. Min Range: -2.6664
Max Act: 2.4403. Min Act: -0.1700
Data Index: 2528014 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6664. Min Range: -2.6664
Max Act: 2.4403. Min Act: -0.1700
Data Index: 2077335 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6664. Min Range: -2.6664
Max Act: 2.4403. Min Act: -0.1700
Data Index: 2818591 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #19