Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 939 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1463. Min Range: -6.1463
Max Act: 6.1151. Min Act: -0.1700
Data Index: 5724180 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1463. Min Range: -6.1463
Max Act: 6.1463. Min Act: -0.1700
Data Index: 7299214 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1463. Min Range: -6.1463
Max Act: 6.0526. Min Act: -0.1700
Data Index: 7457825 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1463. Min Range: -6.1463
Max Act: 5.8963. Min Act: -0.1700
Data Index: 2144012 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1463. Min Range: -6.1463
Max Act: 5.8963. Min Act: -0.1700
Data Index: 2153344 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1463. Min Range: -6.1463
Max Act: 5.8338. Min Act: -0.1700
Data Index: 8713682 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1463. Min Range: -6.1463
Max Act: 5.8026. Min Act: -0.1700
Data Index: 7944153 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1463. Min Range: -6.1463
Max Act: 5.8026. Min Act: -0.1700
Data Index: 3469792 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1463. Min Range: -6.1463
Max Act: 5.8026. Min Act: -0.1700
Data Index: 782811 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1463. Min Range: -6.1463
Max Act: 5.8026. Min Act: -0.1700
Data Index: 3539413 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1463. Min Range: -6.1463
Max Act: 5.7713. Min Act: -0.1700
Data Index: 2335783 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1463. Min Range: -6.1463
Max Act: 5.7713. Min Act: -0.1700
Data Index: 4094518 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1463. Min Range: -6.1463
Max Act: 5.7713. Min Act: -0.1700
Data Index: 7952763 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1463. Min Range: -6.1463
Max Act: 5.7401. Min Act: -0.1700
Data Index: 8524692 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1463. Min Range: -6.1463
Max Act: 5.7401. Min Act: -0.1700
Data Index: 4992448 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1463. Min Range: -6.1463
Max Act: 5.7088. Min Act: -0.1700
Data Index: 7491131 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1463. Min Range: -6.1463
Max Act: 5.7401. Min Act: -0.1700
Data Index: 4183990 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1463. Min Range: -6.1463
Max Act: 5.7088. Min Act: -0.1700
Data Index: 7491133 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1463. Min Range: -6.1463
Max Act: 5.7088. Min Act: -0.1700
Data Index: 7299215 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1463. Min Range: -6.1463
Max Act: 5.7088. Min Act: -0.1700
Data Index: 6700230 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19