Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5423 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7826. Min Range: -5.7826
Max Act: 5.7826. Min Act: -0.1700
Data Index: 214001 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7826. Min Range: -5.7826
Max Act: 5.6888. Min Act: -0.1700
Data Index: 6557031 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7826. Min Range: -5.7826
Max Act: 5.6888. Min Act: -0.1700
Data Index: 3629191 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7826. Min Range: -5.7826
Max Act: 5.6263. Min Act: -0.1700
Data Index: 3100609 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7826. Min Range: -5.7826
Max Act: 5.6576. Min Act: -0.1700
Data Index: 8572144 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7826. Min Range: -5.7826
Max Act: 5.5951. Min Act: -0.1700
Data Index: 6634465 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7826. Min Range: -5.7826
Max Act: 5.5638. Min Act: -0.1700
Data Index: 2766244 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7826. Min Range: -5.7826
Max Act: 5.5326. Min Act: -0.1700
Data Index: 7887965 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7826. Min Range: -5.7826
Max Act: 5.5326. Min Act: -0.1700
Data Index: 274464 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7826. Min Range: -5.7826
Max Act: 5.5326. Min Act: -0.1700
Data Index: 3032762 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7826. Min Range: -5.7826
Max Act: 5.5013. Min Act: -0.1700
Data Index: 7267797 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7826. Min Range: -5.7826
Max Act: 5.4701. Min Act: -0.1700
Data Index: 3586558 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7826. Min Range: -5.7826
Max Act: 5.4388. Min Act: -0.1700
Data Index: 4646634 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7826. Min Range: -5.7826
Max Act: 5.4388. Min Act: -0.1700
Data Index: 1200175 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7826. Min Range: -5.7826
Max Act: 5.4076. Min Act: -0.1700
Data Index: 6344686 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7826. Min Range: -5.7826
Max Act: 5.4076. Min Act: -0.1700
Data Index: 7921163 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7826. Min Range: -5.7826
Max Act: 5.3763. Min Act: -0.1700
Data Index: 5899078 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7826. Min Range: -5.7826
Max Act: 5.3763. Min Act: -0.1700
Data Index: 765864 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7826. Min Range: -5.7826
Max Act: 5.3763. Min Act: -0.1700
Data Index: 368824 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7826. Min Range: -5.7826
Max Act: 5.3763. Min Act: -0.1700
Data Index: 6003883 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #19