Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5070 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5672. Min Range: -4.5672
Max Act: 4.5672. Min Act: -0.1700
Data Index: 1977343 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5672. Min Range: -4.5672
Max Act: 4.5047. Min Act: -0.1700
Data Index: 1812373 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5672. Min Range: -4.5672
Max Act: 4.5047. Min Act: -0.1700
Data Index: 7385133 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5672. Min Range: -4.5672
Max Act: 4.4734. Min Act: -0.1700
Data Index: 4905554 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5672. Min Range: -4.5672
Max Act: 4.4109. Min Act: -0.1700
Data Index: 5485177 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5672. Min Range: -4.5672
Max Act: 4.3797. Min Act: -0.1700
Data Index: 7875762 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5672. Min Range: -4.5672
Max Act: 4.3797. Min Act: -0.1700
Data Index: 2228854 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5672. Min Range: -4.5672
Max Act: 4.4109. Min Act: -0.1700
Data Index: 1553714 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5672. Min Range: -4.5672
Max Act: 4.4109. Min Act: -0.1700
Data Index: 990532 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5672. Min Range: -4.5672
Max Act: 4.3484. Min Act: -0.1700
Data Index: 5528583 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5672. Min Range: -4.5672
Max Act: 4.3797. Min Act: -0.1700
Data Index: 1986266 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5672. Min Range: -4.5672
Max Act: 4.3172. Min Act: -0.1700
Data Index: 4728252 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5672. Min Range: -4.5672
Max Act: 4.3484. Min Act: -0.1700
Data Index: 8476807 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5672. Min Range: -4.5672
Max Act: 4.3484. Min Act: -0.1700
Data Index: 1667370 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5672. Min Range: -4.5672
Max Act: 4.3172. Min Act: -0.1700
Data Index: 3213654 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5672. Min Range: -4.5672
Max Act: 4.2859. Min Act: -0.1700
Data Index: 1627316 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5672. Min Range: -4.5672
Max Act: 4.3172. Min Act: -0.1700
Data Index: 209959 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5672. Min Range: -4.5672
Max Act: 4.3172. Min Act: -0.1700
Data Index: 5735823 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5672. Min Range: -4.5672
Max Act: 4.2859. Min Act: -0.1700
Data Index: 8230690 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5672. Min Range: -4.5672
Max Act: 4.3172. Min Act: -0.1700
Data Index: 4638445 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19