Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2681 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4439. Min Range: -7.4439
Max Act: 7.4439. Min Act: -0.1700
Data Index: 934700 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4439. Min Range: -7.4439
Max Act: 7.4127. Min Act: -0.1700
Data Index: 6832020 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4439. Min Range: -7.4439
Max Act: 7.3502. Min Act: -0.1700
Data Index: 1939679 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4439. Min Range: -7.4439
Max Act: 7.2877. Min Act: -0.1700
Data Index: 4637378 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4439. Min Range: -7.4439
Max Act: 7.2252. Min Act: -0.1700
Data Index: 4184584 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4439. Min Range: -7.4439
Max Act: 7.2252. Min Act: -0.1700
Data Index: 7049952 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4439. Min Range: -7.4439
Max Act: 7.2252. Min Act: -0.1700
Data Index: 2183484 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4439. Min Range: -7.4439
Max Act: 7.1627. Min Act: -0.1700
Data Index: 440556 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4439. Min Range: -7.4439
Max Act: 7.1627. Min Act: -0.1700
Data Index: 6964406 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4439. Min Range: -7.4439
Max Act: 7.1314. Min Act: -0.1700
Data Index: 3302068 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4439. Min Range: -7.4439
Max Act: 7.1314. Min Act: -0.1700
Data Index: 6161508 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4439. Min Range: -7.4439
Max Act: 7.1314. Min Act: -0.1700
Data Index: 7965423 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4439. Min Range: -7.4439
Max Act: 7.1002. Min Act: -0.1700
Data Index: 3475807 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4439. Min Range: -7.4439
Max Act: 7.1002. Min Act: -0.1700
Data Index: 5526739 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4439. Min Range: -7.4439
Max Act: 7.0689. Min Act: -0.1700
Data Index: 516986 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4439. Min Range: -7.4439
Max Act: 7.0689. Min Act: -0.1700
Data Index: 949044 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4439. Min Range: -7.4439
Max Act: 7.0689. Min Act: -0.1700
Data Index: 8097734 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4439. Min Range: -7.4439
Max Act: 7.1002. Min Act: -0.1700
Data Index: 137129 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4439. Min Range: -7.4439
Max Act: 7.0377. Min Act: -0.1700
Data Index: 5042266 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4439. Min Range: -7.4439
Max Act: 7.0377. Min Act: -0.1700
Data Index: 3939743 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19