Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5080 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0515. Min Range: -5.0515
Max Act: 5.0515. Min Act: -0.1700
Data Index: 4280633 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0515. Min Range: -5.0515
Max Act: 4.9890. Min Act: -0.1700
Data Index: 1865311 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0515. Min Range: -5.0515
Max Act: 4.9265. Min Act: -0.1700
Data Index: 6161905 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0515. Min Range: -5.0515
Max Act: 4.8327. Min Act: -0.1700
Data Index: 141141 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0515. Min Range: -5.0515
Max Act: 4.8327. Min Act: -0.1700
Data Index: 3283375 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0515. Min Range: -5.0515
Max Act: 4.8327. Min Act: -0.1700
Data Index: 246168 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0515. Min Range: -5.0515
Max Act: 4.7390. Min Act: -0.1700
Data Index: 8026678 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0515. Min Range: -5.0515
Max Act: 4.7390. Min Act: -0.1700
Data Index: 7424399 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0515. Min Range: -5.0515
Max Act: 4.7390. Min Act: -0.1700
Data Index: 855324 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0515. Min Range: -5.0515
Max Act: 4.7077. Min Act: -0.1700
Data Index: 2157691 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0515. Min Range: -5.0515
Max Act: 4.7077. Min Act: -0.1700
Data Index: 6753521 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0515. Min Range: -5.0515
Max Act: 4.6765. Min Act: -0.1700
Data Index: 6194616 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0515. Min Range: -5.0515
Max Act: 4.6765. Min Act: -0.1700
Data Index: 4110609 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0515. Min Range: -5.0515
Max Act: 4.6765. Min Act: -0.1700
Data Index: 4267167 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0515. Min Range: -5.0515
Max Act: 4.6765. Min Act: -0.1700
Data Index: 6586075 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0515. Min Range: -5.0515
Max Act: 4.6765. Min Act: -0.1700
Data Index: 1952983 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0515. Min Range: -5.0515
Max Act: 4.6452. Min Act: -0.1700
Data Index: 1865989 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0515. Min Range: -5.0515
Max Act: 4.6452. Min Act: -0.1700
Data Index: 3551043 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0515. Min Range: -5.0515
Max Act: 4.6452. Min Act: -0.1700
Data Index: 4652218 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0515. Min Range: -5.0515
Max Act: 4.6140. Min Act: -0.1700
Data Index: 3901422 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19