Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3020 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9607. Min Range: -7.9607
Max Act: 7.9607. Min Act: -0.1700
Data Index: 4143169 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9607. Min Range: -7.9607
Max Act: 7.8982. Min Act: -0.1700
Data Index: 6543006 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9607. Min Range: -7.9607
Max Act: 7.8669. Min Act: -0.1700
Data Index: 6624047 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9607. Min Range: -7.9607
Max Act: 7.5857. Min Act: -0.1700
Data Index: 7021748 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9607. Min Range: -7.9607
Max Act: 7.4919. Min Act: -0.1700
Data Index: 204451 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9607. Min Range: -7.9607
Max Act: 7.4294. Min Act: -0.1700
Data Index: 2049767 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9607. Min Range: -7.9607
Max Act: 7.3982. Min Act: -0.1700
Data Index: 1753293 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9607. Min Range: -7.9607
Max Act: 7.3357. Min Act: -0.1700
Data Index: 4643457 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9607. Min Range: -7.9607
Max Act: 7.3357. Min Act: -0.1700
Data Index: 4721412 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9607. Min Range: -7.9607
Max Act: 7.2732. Min Act: -0.1700
Data Index: 3077804 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9607. Min Range: -7.9607
Max Act: 7.2732. Min Act: -0.1700
Data Index: 8571398 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9607. Min Range: -7.9607
Max Act: 7.2732. Min Act: -0.1700
Data Index: 417355 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9607. Min Range: -7.9607
Max Act: 7.2419. Min Act: -0.1700
Data Index: 5610629 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9607. Min Range: -7.9607
Max Act: 7.2107. Min Act: -0.1700
Data Index: 5708542 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9607. Min Range: -7.9607
Max Act: 7.2107. Min Act: -0.1700
Data Index: 3299318 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9607. Min Range: -7.9607
Max Act: 7.2107. Min Act: -0.1700
Data Index: 1893812 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9607. Min Range: -7.9607
Max Act: 7.2419. Min Act: -0.1700
Data Index: 6234305 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9607. Min Range: -7.9607
Max Act: 7.2107. Min Act: -0.1700
Data Index: 3872281 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9607. Min Range: -7.9607
Max Act: 7.1794. Min Act: -0.1700
Data Index: 3864452 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9607. Min Range: -7.9607
Max Act: 7.1794. Min Act: -0.1700
Data Index: 360370 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19