Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3029 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2006. Min Range: -6.2006
Max Act: 6.2006. Min Act: -0.1700
Data Index: 8745303 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2006. Min Range: -6.2006
Max Act: 6.2006. Min Act: -0.1700
Data Index: 1202291 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2006. Min Range: -6.2006
Max Act: 6.1694. Min Act: -0.1700
Data Index: 1202296 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2006. Min Range: -6.2006
Max Act: 6.1694. Min Act: -0.1700
Data Index: 5046266 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2006. Min Range: -6.2006
Max Act: 6.1381. Min Act: -0.1700
Data Index: 7593069 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2006. Min Range: -6.2006
Max Act: 6.1069. Min Act: -0.1700
Data Index: 2029150 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2006. Min Range: -6.2006
Max Act: 6.1069. Min Act: -0.1700
Data Index: 4793745 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2006. Min Range: -6.2006
Max Act: 6.0756. Min Act: -0.1700
Data Index: 2478942 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2006. Min Range: -6.2006
Max Act: 6.0756. Min Act: -0.1700
Data Index: 5819519 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2006. Min Range: -6.2006
Max Act: 6.0756. Min Act: -0.1700
Data Index: 3103584 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2006. Min Range: -6.2006
Max Act: 6.0756. Min Act: -0.1700
Data Index: 3998958 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2006. Min Range: -6.2006
Max Act: 6.1069. Min Act: -0.1700
Data Index: 4339072 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2006. Min Range: -6.2006
Max Act: 6.0444. Min Act: -0.1700
Data Index: 1202297 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2006. Min Range: -6.2006
Max Act: 6.0444. Min Act: -0.1700
Data Index: 8141317 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2006. Min Range: -6.2006
Max Act: 6.0444. Min Act: -0.1700
Data Index: 3103574 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2006. Min Range: -6.2006
Max Act: 6.0444. Min Act: -0.1700
Data Index: 7982605 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2006. Min Range: -6.2006
Max Act: 6.0131. Min Act: -0.1700
Data Index: 3398514 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2006. Min Range: -6.2006
Max Act: 6.0444. Min Act: -0.1700
Data Index: 1202294 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2006. Min Range: -6.2006
Max Act: 5.9819. Min Act: -0.1700
Data Index: 2814232 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2006. Min Range: -6.2006
Max Act: 5.9819. Min Act: -0.1700
Data Index: 5511230 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19