Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2862 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7116. Min Range: -8.7116
Max Act: 8.7116. Min Act: -0.1700
Data Index: 5403606 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7116. Min Range: -8.7116
Max Act: 8.7116. Min Act: -0.1700
Data Index: 2883841 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7116. Min Range: -8.7116
Max Act: 8.3366. Min Act: -0.1700
Data Index: 5593107 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7116. Min Range: -8.7116
Max Act: 8.1491. Min Act: -0.1700
Data Index: 3859276 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7116. Min Range: -8.7116
Max Act: 8.1491. Min Act: -0.1700
Data Index: 5277058 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7116. Min Range: -8.7116
Max Act: 8.1491. Min Act: -0.1700
Data Index: 579691 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7116. Min Range: -8.7116
Max Act: 8.0241. Min Act: -0.1700
Data Index: 1536694 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7116. Min Range: -8.7116
Max Act: 8.0241. Min Act: -0.1700
Data Index: 4198694 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7116. Min Range: -8.7116
Max Act: 8.0241. Min Act: -0.1700
Data Index: 2096989 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7116. Min Range: -8.7116
Max Act: 8.0241. Min Act: -0.1700
Data Index: 1129561 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7116. Min Range: -8.7116
Max Act: 7.9616. Min Act: -0.1700
Data Index: 3701130 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7116. Min Range: -8.7116
Max Act: 7.9616. Min Act: -0.1700
Data Index: 2961330 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7116. Min Range: -8.7116
Max Act: 7.9616. Min Act: -0.1700
Data Index: 2490224 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7116. Min Range: -8.7116
Max Act: 7.9616. Min Act: -0.1700
Data Index: 2961329 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7116. Min Range: -8.7116
Max Act: 7.8991. Min Act: -0.1700
Data Index: 4606294 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7116. Min Range: -8.7116
Max Act: 7.8991. Min Act: -0.1700
Data Index: 375777 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7116. Min Range: -8.7116
Max Act: 7.8991. Min Act: -0.1700
Data Index: 8341274 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7116. Min Range: -8.7116
Max Act: 7.8991. Min Act: -0.1700
Data Index: 7704281 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7116. Min Range: -8.7116
Max Act: 7.8991. Min Act: -0.1700
Data Index: 3793455 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7116. Min Range: -8.7116
Max Act: 7.8991. Min Act: -0.1700
Data Index: 2261752 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #19