Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3443 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0687. Min Range: -7.0687
Max Act: 7.0687. Min Act: -0.1700
Data Index: 6745297 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0687. Min Range: -7.0687
Max Act: 7.0374. Min Act: -0.1700
Data Index: 688161 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0687. Min Range: -7.0687
Max Act: 7.0374. Min Act: -0.1700
Data Index: 6033094 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0687. Min Range: -7.0687
Max Act: 6.9437. Min Act: -0.1700
Data Index: 2521475 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0687. Min Range: -7.0687
Max Act: 6.9124. Min Act: -0.1700
Data Index: 1221287 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0687. Min Range: -7.0687
Max Act: 6.8812. Min Act: -0.1700
Data Index: 5034808 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0687. Min Range: -7.0687
Max Act: 6.8812. Min Act: -0.1700
Data Index: 6745298 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0687. Min Range: -7.0687
Max Act: 6.8812. Min Act: -0.1700
Data Index: 4918321 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0687. Min Range: -7.0687
Max Act: 6.8812. Min Act: -0.1700
Data Index: 127531 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0687. Min Range: -7.0687
Max Act: 6.8812. Min Act: -0.1700
Data Index: 5260576 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0687. Min Range: -7.0687
Max Act: 6.8812. Min Act: -0.1700
Data Index: 3961390 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0687. Min Range: -7.0687
Max Act: 6.8499. Min Act: -0.1700
Data Index: 2364902 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0687. Min Range: -7.0687
Max Act: 6.8187. Min Act: -0.1700
Data Index: 8438042 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0687. Min Range: -7.0687
Max Act: 6.8499. Min Act: -0.1700
Data Index: 7070716 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0687. Min Range: -7.0687
Max Act: 6.8187. Min Act: -0.1700
Data Index: 3295053 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0687. Min Range: -7.0687
Max Act: 6.8187. Min Act: -0.1700
Data Index: 835120 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0687. Min Range: -7.0687
Max Act: 6.8187. Min Act: -0.1700
Data Index: 7170254 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0687. Min Range: -7.0687
Max Act: 6.8187. Min Act: -0.1700
Data Index: 3295051 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0687. Min Range: -7.0687
Max Act: 6.8187. Min Act: -0.1700
Data Index: 7023629 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0687. Min Range: -7.0687
Max Act: 6.8187. Min Act: -0.1700
Data Index: 43575 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #19