Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2788 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5277. Min Range: -6.5277
Max Act: 6.5277. Min Act: -0.1700
Data Index: 6653605 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5277. Min Range: -6.5277
Max Act: 6.1839. Min Act: -0.1700
Data Index: 2475261 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5277. Min Range: -6.5277
Max Act: 6.1527. Min Act: -0.1700
Data Index: 2627152 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5277. Min Range: -6.5277
Max Act: 6.1214. Min Act: -0.1700
Data Index: 150873 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5277. Min Range: -6.5277
Max Act: 6.0589. Min Act: -0.1700
Data Index: 970691 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5277. Min Range: -6.5277
Max Act: 6.0277. Min Act: -0.1700
Data Index: 4348907 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5277. Min Range: -6.5277
Max Act: 5.9652. Min Act: -0.1700
Data Index: 6339202 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5277. Min Range: -6.5277
Max Act: 5.8714. Min Act: -0.1700
Data Index: 8442498 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5277. Min Range: -6.5277
Max Act: 5.7777. Min Act: -0.1700
Data Index: 468514 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5277. Min Range: -6.5277
Max Act: 5.7777. Min Act: -0.1700
Data Index: 7700441 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5277. Min Range: -6.5277
Max Act: 5.7464. Min Act: -0.1700
Data Index: 3014582 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5277. Min Range: -6.5277
Max Act: 5.7777. Min Act: -0.1700
Data Index: 1584462 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5277. Min Range: -6.5277
Max Act: 5.7152. Min Act: -0.1700
Data Index: 1607966 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5277. Min Range: -6.5277
Max Act: 5.7152. Min Act: -0.1700
Data Index: 3671596 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5277. Min Range: -6.5277
Max Act: 5.7464. Min Act: -0.1700
Data Index: 1703555 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5277. Min Range: -6.5277
Max Act: 5.6839. Min Act: -0.1700
Data Index: 369005 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5277. Min Range: -6.5277
Max Act: 5.6527. Min Act: -0.1700
Data Index: 874477 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5277. Min Range: -6.5277
Max Act: 5.6527. Min Act: -0.1700
Data Index: 8350508 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5277. Min Range: -6.5277
Max Act: 5.6527. Min Act: -0.1700
Data Index: 448495 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5277. Min Range: -6.5277
Max Act: 5.6214. Min Act: -0.1700
Data Index: 2753310 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #19