Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1370 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1126. Min Range: -9.1126
Max Act: 9.1126. Min Act: -0.1700
Data Index: 6918425 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1126. Min Range: -9.1126
Max Act: 9.0501. Min Act: -0.1700
Data Index: 5355939 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1126. Min Range: -9.1126
Max Act: 9.1126. Min Act: -0.1700
Data Index: 596205 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1126. Min Range: -9.1126
Max Act: 8.9876. Min Act: -0.1700
Data Index: 3486307 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1126. Min Range: -9.1126
Max Act: 8.8626. Min Act: -0.1700
Data Index: 6799959 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1126. Min Range: -9.1126
Max Act: 8.8001. Min Act: -0.1700
Data Index: 2270612 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1126. Min Range: -9.1126
Max Act: 8.7376. Min Act: -0.1700
Data Index: 8123022 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1126. Min Range: -9.1126
Max Act: 8.7376. Min Act: -0.1700
Data Index: 4663115 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1126. Min Range: -9.1126
Max Act: 8.7376. Min Act: -0.1700
Data Index: 2704250 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1126. Min Range: -9.1126
Max Act: 8.5501. Min Act: -0.1700
Data Index: 1778723 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1126. Min Range: -9.1126
Max Act: 8.6126. Min Act: -0.1700
Data Index: 3461853 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1126. Min Range: -9.1126
Max Act: 8.6126. Min Act: -0.1700
Data Index: 2485093 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1126. Min Range: -9.1126
Max Act: 8.5501. Min Act: -0.1700
Data Index: 3254216 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1126. Min Range: -9.1126
Max Act: 8.5501. Min Act: -0.1700
Data Index: 3293968 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1126. Min Range: -9.1126
Max Act: 8.5501. Min Act: -0.1700
Data Index: 1492077 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1126. Min Range: -9.1126
Max Act: 8.5501. Min Act: -0.1700
Data Index: 4907356 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1126. Min Range: -9.1126
Max Act: 8.4876. Min Act: -0.1700
Data Index: 666357 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1126. Min Range: -9.1126
Max Act: 8.5501. Min Act: -0.1700
Data Index: 2628114 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1126. Min Range: -9.1126
Max Act: 8.5501. Min Act: -0.1700
Data Index: 1747318 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1126. Min Range: -9.1126
Max Act: 8.5501. Min Act: -0.1700
Data Index: 3848547 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19