Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3028 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4343. Min Range: -5.4343
Max Act: 5.4343. Min Act: -0.1700
Data Index: 4545851 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4343. Min Range: -5.4343
Max Act: 5.3093. Min Act: -0.1700
Data Index: 1440425 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4343. Min Range: -5.4343
Max Act: 5.2780. Min Act: -0.1700
Data Index: 7216836 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4343. Min Range: -5.4343
Max Act: 5.2780. Min Act: -0.1700
Data Index: 4599535 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4343. Min Range: -5.4343
Max Act: 5.2468. Min Act: -0.1700
Data Index: 7110474 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4343. Min Range: -5.4343
Max Act: 5.1843. Min Act: -0.1700
Data Index: 1525082 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4343. Min Range: -5.4343
Max Act: 5.1843. Min Act: -0.1700
Data Index: 2296321 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4343. Min Range: -5.4343
Max Act: 5.1530. Min Act: -0.1700
Data Index: 6981358 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4343. Min Range: -5.4343
Max Act: 5.1218. Min Act: -0.1700
Data Index: 3969544 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4343. Min Range: -5.4343
Max Act: 5.1530. Min Act: -0.1700
Data Index: 2458514 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4343. Min Range: -5.4343
Max Act: 5.1218. Min Act: -0.1700
Data Index: 2835697 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4343. Min Range: -5.4343
Max Act: 5.1218. Min Act: -0.1700
Data Index: 7693125 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4343. Min Range: -5.4343
Max Act: 5.0905. Min Act: -0.1700
Data Index: 6887365 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4343. Min Range: -5.4343
Max Act: 5.0905. Min Act: -0.1700
Data Index: 4538461 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4343. Min Range: -5.4343
Max Act: 5.0905. Min Act: -0.1700
Data Index: 174984 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4343. Min Range: -5.4343
Max Act: 5.0905. Min Act: -0.1700
Data Index: 4572392 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4343. Min Range: -5.4343
Max Act: 5.0593. Min Act: -0.1699
Data Index: 385294 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4343. Min Range: -5.4343
Max Act: 5.0593. Min Act: -0.1698
Data Index: 2663771 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4343. Min Range: -5.4343
Max Act: 5.0593. Min Act: -0.1700
Data Index: 4447545 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4343. Min Range: -5.4343
Max Act: 5.0593. Min Act: -0.1700
Data Index: 3806465 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #19