Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 409 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9492. Min Range: -5.9492
Max Act: 5.9492. Min Act: -0.1700
Data Index: 2996177 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9492. Min Range: -5.9492
Max Act: 5.9492. Min Act: -0.1700
Data Index: 5434500 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9492. Min Range: -5.9492
Max Act: 5.7304. Min Act: -0.1700
Data Index: 6413385 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9492. Min Range: -5.9492
Max Act: 5.6992. Min Act: -0.1700
Data Index: 6413387 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9492. Min Range: -5.9492
Max Act: 5.6992. Min Act: -0.1700
Data Index: 2996171 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9492. Min Range: -5.9492
Max Act: 5.6679. Min Act: -0.1700
Data Index: 2996172 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9492. Min Range: -5.9492
Max Act: 5.6679. Min Act: -0.1700
Data Index: 6413386 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9492. Min Range: -5.9492
Max Act: 5.5742. Min Act: -0.1700
Data Index: 6413395 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9492. Min Range: -5.9492
Max Act: 5.5429. Min Act: -0.1700
Data Index: 6413397 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9492. Min Range: -5.9492
Max Act: 5.5429. Min Act: -0.1700
Data Index: 2996166 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9492. Min Range: -5.9492
Max Act: 5.5117. Min Act: -0.1700
Data Index: 7116268 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9492. Min Range: -5.9492
Max Act: 5.4179. Min Act: -0.1700
Data Index: 2996162 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9492. Min Range: -5.9492
Max Act: 5.3867. Min Act: -0.1700
Data Index: 7116279 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9492. Min Range: -5.9492
Max Act: 5.3554. Min Act: -0.1700
Data Index: 689501 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9492. Min Range: -5.9492
Max Act: 5.3554. Min Act: -0.1700
Data Index: 2200911 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9492. Min Range: -5.9492
Max Act: 5.3242. Min Act: -0.1700
Data Index: 1403704 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9492. Min Range: -5.9492
Max Act: 5.3242. Min Act: -0.1700
Data Index: 7116277 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9492. Min Range: -5.9492
Max Act: 5.3242. Min Act: -0.1700
Data Index: 5272023 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9492. Min Range: -5.9492
Max Act: 5.2929. Min Act: -0.1700
Data Index: 5807495 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9492. Min Range: -5.9492
Max Act: 5.2929. Min Act: -0.1700
Data Index: 3254977 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19