Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2782 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7147. Min Range: -9.7147
Max Act: 9.7147. Min Act: -0.1700
Data Index: 6943611 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7147. Min Range: -9.7147
Max Act: 9.5272. Min Act: -0.1700
Data Index: 3344509 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7147. Min Range: -9.7147
Max Act: 9.4022. Min Act: -0.1700
Data Index: 5928046 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7147. Min Range: -9.7147
Max Act: 9.4647. Min Act: -0.1700
Data Index: 2330926 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7147. Min Range: -9.7147
Max Act: 9.4647. Min Act: -0.1700
Data Index: 7823691 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7147. Min Range: -9.7147
Max Act: 9.4022. Min Act: -0.1700
Data Index: 4022476 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7147. Min Range: -9.7147
Max Act: 9.4022. Min Act: -0.1700
Data Index: 4289992 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7147. Min Range: -9.7147
Max Act: 9.4647. Min Act: -0.1700
Data Index: 6046628 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7147. Min Range: -9.7147
Max Act: 9.4022. Min Act: -0.1700
Data Index: 3852376 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7147. Min Range: -9.7147
Max Act: 9.3397. Min Act: -0.1700
Data Index: 5621622 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7147. Min Range: -9.7147
Max Act: 9.3397. Min Act: -0.1700
Data Index: 1798281 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7147. Min Range: -9.7147
Max Act: 9.3397. Min Act: -0.1700
Data Index: 8777641 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7147. Min Range: -9.7147
Max Act: 9.3397. Min Act: -0.1700
Data Index: 5882280 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7147. Min Range: -9.7147
Max Act: 9.2772. Min Act: -0.1700
Data Index: 7861668 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7147. Min Range: -9.7147
Max Act: 9.2772. Min Act: -0.1700
Data Index: 4483107 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7147. Min Range: -9.7147
Max Act: 9.2147. Min Act: -0.1700
Data Index: 1506968 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7147. Min Range: -9.7147
Max Act: 9.2147. Min Act: -0.1700
Data Index: 2466802 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7147. Min Range: -9.7147
Max Act: 9.2147. Min Act: -0.1700
Data Index: 1031914 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7147. Min Range: -9.7147
Max Act: 9.2147. Min Act: -0.1700
Data Index: 607265 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7147. Min Range: -9.7147
Max Act: 9.2147. Min Act: -0.1700
Data Index: 5753035 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #19