Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2059 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6505. Min Range: -3.6505
Max Act: 3.6505. Min Act: -0.1700
Data Index: 566013 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6505. Min Range: -3.6505
Max Act: 3.3372. Min Act: -0.1700
Data Index: 8043406 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6505. Min Range: -3.6505
Max Act: 3.3372. Min Act: -0.1700
Data Index: 8702043 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6505. Min Range: -3.6505
Max Act: 3.2430. Min Act: -0.1700
Data Index: 3777362 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6505. Min Range: -3.6505
Max Act: 3.1959. Min Act: -0.1700
Data Index: 5883815 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6505. Min Range: -3.6505
Max Act: 3.1644. Min Act: -0.1700
Data Index: 4020821 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6505. Min Range: -3.6505
Max Act: 3.1644. Min Act: -0.1700
Data Index: 6215631 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6505. Min Range: -3.6505
Max Act: 3.1644. Min Act: -0.1700
Data Index: 1737423 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6505. Min Range: -3.6505
Max Act: 3.1487. Min Act: -0.1700
Data Index: 2523028 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6505. Min Range: -3.6505
Max Act: 3.1329. Min Act: -0.1700
Data Index: 7973332 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6505. Min Range: -3.6505
Max Act: 3.1487. Min Act: -0.1700
Data Index: 6271726 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6505. Min Range: -3.6505
Max Act: 3.1329. Min Act: -0.1700
Data Index: 6661429 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6505. Min Range: -3.6505
Max Act: 3.1172. Min Act: -0.1700
Data Index: 1273429 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6505. Min Range: -3.6505
Max Act: 3.1172. Min Act: -0.1700
Data Index: 2594059 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6505. Min Range: -3.6505
Max Act: 3.1014. Min Act: -0.1700
Data Index: 8138675 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6505. Min Range: -3.6505
Max Act: 3.1014. Min Act: -0.1700
Data Index: 4247079 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6505. Min Range: -3.6505
Max Act: 3.1172. Min Act: -0.1700
Data Index: 282174 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6505. Min Range: -3.6505
Max Act: 3.0856. Min Act: -0.1700
Data Index: 1884441 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6505. Min Range: -3.6505
Max Act: 3.0699. Min Act: -0.1700
Data Index: 6535805 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6505. Min Range: -3.6505
Max Act: 3.0699. Min Act: -0.1700
Data Index: 1354828 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #19