Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 695 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9373. Min Range: -6.9373
Max Act: 6.9373. Min Act: -0.1700
Data Index: 5382965 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9373. Min Range: -6.9373
Max Act: 6.6561. Min Act: -0.1700
Data Index: 51904 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9373. Min Range: -6.9373
Max Act: 6.6248. Min Act: -0.1700
Data Index: 8069612 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9373. Min Range: -6.9373
Max Act: 6.5936. Min Act: -0.1700
Data Index: 3343804 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9373. Min Range: -6.9373
Max Act: 6.5623. Min Act: -0.1700
Data Index: 7924102 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9373. Min Range: -6.9373
Max Act: 6.5623. Min Act: -0.1700
Data Index: 1019409 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9373. Min Range: -6.9373
Max Act: 6.5936. Min Act: -0.1700
Data Index: 682791 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9373. Min Range: -6.9373
Max Act: 6.5623. Min Act: -0.1700
Data Index: 5883578 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9373. Min Range: -6.9373
Max Act: 6.5311. Min Act: -0.1700
Data Index: 4759017 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9373. Min Range: -6.9373
Max Act: 6.5311. Min Act: -0.1700
Data Index: 8339992 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9373. Min Range: -6.9373
Max Act: 6.5311. Min Act: -0.1700
Data Index: 8325914 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9373. Min Range: -6.9373
Max Act: 6.4998. Min Act: -0.1700
Data Index: 2777045 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9373. Min Range: -6.9373
Max Act: 6.4998. Min Act: -0.1700
Data Index: 5714198 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9373. Min Range: -6.9373
Max Act: 6.4998. Min Act: -0.1700
Data Index: 397851 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9373. Min Range: -6.9373
Max Act: 6.4373. Min Act: -0.1700
Data Index: 4466905 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9373. Min Range: -6.9373
Max Act: 6.4686. Min Act: -0.1700
Data Index: 6650664 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9373. Min Range: -6.9373
Max Act: 6.4686. Min Act: -0.1700
Data Index: 6575185 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9373. Min Range: -6.9373
Max Act: 6.4373. Min Act: -0.1700
Data Index: 7666396 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9373. Min Range: -6.9373
Max Act: 6.4061. Min Act: -0.1700
Data Index: 5901370 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9373. Min Range: -6.9373
Max Act: 6.4061. Min Act: -0.1700
Data Index: 5138295 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19