Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1425 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7344. Min Range: -7.7344
Max Act: 7.7344. Min Act: -0.1700
Data Index: 5098467 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7344. Min Range: -7.7344
Max Act: 7.6094. Min Act: -0.1700
Data Index: 7476400 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7344. Min Range: -7.7344
Max Act: 7.3907. Min Act: -0.1700
Data Index: 7661630 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7344. Min Range: -7.7344
Max Act: 7.1094. Min Act: -0.1700
Data Index: 443665 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7344. Min Range: -7.7344
Max Act: 7.0469. Min Act: -0.1700
Data Index: 4991692 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7344. Min Range: -7.7344
Max Act: 6.9844. Min Act: -0.1700
Data Index: 8144949 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7344. Min Range: -7.7344
Max Act: 6.9532. Min Act: -0.1700
Data Index: 6329545 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7344. Min Range: -7.7344
Max Act: 6.9532. Min Act: -0.1700
Data Index: 8342926 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7344. Min Range: -7.7344
Max Act: 6.8907. Min Act: -0.1700
Data Index: 576620 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7344. Min Range: -7.7344
Max Act: 6.8907. Min Act: -0.1700
Data Index: 6771061 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7344. Min Range: -7.7344
Max Act: 6.8594. Min Act: -0.1700
Data Index: 2090690 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7344. Min Range: -7.7344
Max Act: 6.8282. Min Act: -0.1700
Data Index: 6352863 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7344. Min Range: -7.7344
Max Act: 6.8282. Min Act: -0.1700
Data Index: 5688297 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7344. Min Range: -7.7344
Max Act: 6.8282. Min Act: -0.1700
Data Index: 163446 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7344. Min Range: -7.7344
Max Act: 6.8282. Min Act: -0.1700
Data Index: 7455412 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7344. Min Range: -7.7344
Max Act: 6.8282. Min Act: -0.1700
Data Index: 8737998 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7344. Min Range: -7.7344
Max Act: 6.7657. Min Act: -0.1700
Data Index: 2453972 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7344. Min Range: -7.7344
Max Act: 6.7344. Min Act: -0.1700
Data Index: 2606126 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7344. Min Range: -7.7344
Max Act: 6.7032. Min Act: -0.1700
Data Index: 3668526 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7344. Min Range: -7.7344
Max Act: 6.7032. Min Act: -0.1700
Data Index: 272780 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #19