Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5826 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.6559. Min Act: -0.1700
Data Index: 6948515 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.5622. Min Act: -0.1700
Data Index: 3338168 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.5622. Min Act: -0.1700
Data Index: 6733492 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.4684. Min Act: -0.1700
Data Index: 4218137 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.4059. Min Act: -0.1700
Data Index: 2650839 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.3434. Min Act: -0.1700
Data Index: 4860952 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.3122. Min Act: -0.1700
Data Index: 2838735 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.3122. Min Act: -0.1700
Data Index: 7486901 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.2809. Min Act: -0.1700
Data Index: 4939987 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.2184. Min Act: -0.1700
Data Index: 5438377 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.2497. Min Act: -0.1700
Data Index: 8166657 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.2497. Min Act: -0.1700
Data Index: 5722592 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.1872. Min Act: -0.1700
Data Index: 5128820 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.1872. Min Act: -0.1700
Data Index: 4840314 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.1559. Min Act: -0.1700
Data Index: 1869358 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.1559. Min Act: -0.1700
Data Index: 2499739 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.1247. Min Act: -0.1700
Data Index: 3990513 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.1247. Min Act: -0.1700
Data Index: 5191822 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.0934. Min Act: -0.1700
Data Index: 6295809 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6559. Min Range: -6.6559
Max Act: 6.0934. Min Act: -0.1700
Data Index: 4843047 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #19