Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2686 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3912. Min Range: -10.3912
Max Act: 10.3912. Min Act: -0.1700
Data Index: 4471759 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3912. Min Range: -10.3912
Max Act: 9.7037. Min Act: -0.1700
Data Index: 1793618 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3912. Min Range: -10.3912
Max Act: 9.6412. Min Act: -0.1700
Data Index: 3056456 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3912. Min Range: -10.3912
Max Act: 9.5787. Min Act: -0.1700
Data Index: 1307168 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3912. Min Range: -10.3912
Max Act: 9.5162. Min Act: -0.1700
Data Index: 6760519 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3912. Min Range: -10.3912
Max Act: 9.5162. Min Act: -0.1700
Data Index: 3607730 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3912. Min Range: -10.3912
Max Act: 9.5162. Min Act: -0.1700
Data Index: 8353751 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3912. Min Range: -10.3912
Max Act: 9.4537. Min Act: -0.1700
Data Index: 5275770 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3912. Min Range: -10.3912
Max Act: 9.4537. Min Act: -0.1700
Data Index: 5203380 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3912. Min Range: -10.3912
Max Act: 9.2037. Min Act: -0.1700
Data Index: 5255469 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3912. Min Range: -10.3912
Max Act: 9.2037. Min Act: -0.1700
Data Index: 2126572 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3912. Min Range: -10.3912
Max Act: 9.2037. Min Act: -0.1700
Data Index: 5789207 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3912. Min Range: -10.3912
Max Act: 9.1412. Min Act: -0.1700
Data Index: 2488614 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3912. Min Range: -10.3912
Max Act: 9.1412. Min Act: -0.1700
Data Index: 8541963 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3912. Min Range: -10.3912
Max Act: 9.1412. Min Act: -0.1700
Data Index: 6097373 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3912. Min Range: -10.3912
Max Act: 9.0162. Min Act: -0.1700
Data Index: 3594790 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3912. Min Range: -10.3912
Max Act: 9.0162. Min Act: -0.1700
Data Index: 5317658 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3912. Min Range: -10.3912
Max Act: 9.0162. Min Act: -0.1700
Data Index: 210445 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3912. Min Range: -10.3912
Max Act: 8.8912. Min Act: -0.1700
Data Index: 5497047 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3912. Min Range: -10.3912
Max Act: 8.8912. Min Act: -0.1700
Data Index: 1239112 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #19