Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2853 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6145. Min Range: -5.6145
Max Act: 5.6145. Min Act: -0.1700
Data Index: 4566081 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6145. Min Range: -5.6145
Max Act: 5.5520. Min Act: -0.1700
Data Index: 7865704 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6145. Min Range: -5.6145
Max Act: 5.5520. Min Act: -0.1700
Data Index: 1200575 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6145. Min Range: -5.6145
Max Act: 5.4582. Min Act: -0.1700
Data Index: 2250351 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6145. Min Range: -5.6145
Max Act: 5.4582. Min Act: -0.1700
Data Index: 5930290 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6145. Min Range: -5.6145
Max Act: 5.3645. Min Act: -0.1700
Data Index: 7865705 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6145. Min Range: -5.6145
Max Act: 5.2707. Min Act: -0.1700
Data Index: 6342718 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6145. Min Range: -5.6145
Max Act: 5.2395. Min Act: -0.1700
Data Index: 1651114 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6145. Min Range: -5.6145
Max Act: 5.2082. Min Act: -0.1700
Data Index: 4782821 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6145. Min Range: -5.6145
Max Act: 5.1457. Min Act: -0.1700
Data Index: 3791209 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6145. Min Range: -5.6145
Max Act: 5.1457. Min Act: -0.1700
Data Index: 1156397 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6145. Min Range: -5.6145
Max Act: 5.1145. Min Act: -0.1700
Data Index: 6981149 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6145. Min Range: -5.6145
Max Act: 5.1770. Min Act: -0.1700
Data Index: 4846881 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6145. Min Range: -5.6145
Max Act: 5.1457. Min Act: -0.1700
Data Index: 2648630 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6145. Min Range: -5.6145
Max Act: 5.1457. Min Act: -0.1700
Data Index: 202696 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6145. Min Range: -5.6145
Max Act: 5.1145. Min Act: -0.1700
Data Index: 6534128 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6145. Min Range: -5.6145
Max Act: 5.1145. Min Act: -0.1700
Data Index: 4330330 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6145. Min Range: -5.6145
Max Act: 5.0832. Min Act: -0.1700
Data Index: 8531246 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6145. Min Range: -5.6145
Max Act: 5.0832. Min Act: -0.1700
Data Index: 6500800 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6145. Min Range: -5.6145
Max Act: 5.0520. Min Act: -0.1700
Data Index: 2710670 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19