Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3004 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6107. Min Range: -4.6107
Max Act: 4.6107. Min Act: -0.1700
Data Index: 7836435 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6107. Min Range: -4.6107
Max Act: 4.5795. Min Act: -0.1700
Data Index: 8069837 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6107. Min Range: -4.6107
Max Act: 4.5170. Min Act: -0.1700
Data Index: 8319724 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6107. Min Range: -4.6107
Max Act: 4.4857. Min Act: -0.1700
Data Index: 3312519 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6107. Min Range: -4.6107
Max Act: 4.3920. Min Act: -0.1700
Data Index: 7366802 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6107. Min Range: -4.6107
Max Act: 4.3607. Min Act: -0.1700
Data Index: 5115217 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6107. Min Range: -4.6107
Max Act: 4.3607. Min Act: -0.1700
Data Index: 1409290 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6107. Min Range: -4.6107
Max Act: 4.3295. Min Act: -0.1700
Data Index: 6508265 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6107. Min Range: -4.6107
Max Act: 4.3295. Min Act: -0.1700
Data Index: 328103 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6107. Min Range: -4.6107
Max Act: 4.2670. Min Act: -0.1700
Data Index: 2694639 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6107. Min Range: -4.6107
Max Act: 4.2982. Min Act: -0.1700
Data Index: 8160609 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6107. Min Range: -4.6107
Max Act: 4.2670. Min Act: -0.1700
Data Index: 791530 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6107. Min Range: -4.6107
Max Act: 4.2357. Min Act: -0.1700
Data Index: 7179425 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6107. Min Range: -4.6107
Max Act: 4.2045. Min Act: -0.1700
Data Index: 5432351 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6107. Min Range: -4.6107
Max Act: 4.2045. Min Act: -0.1700
Data Index: 4844614 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6107. Min Range: -4.6107
Max Act: 4.2045. Min Act: -0.1700
Data Index: 6916833 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6107. Min Range: -4.6107
Max Act: 4.1732. Min Act: -0.1700
Data Index: 4878252 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6107. Min Range: -4.6107
Max Act: 4.1732. Min Act: -0.1700
Data Index: 6641875 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6107. Min Range: -4.6107
Max Act: 4.1732. Min Act: -0.1700
Data Index: 4498672 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6107. Min Range: -4.6107
Max Act: 4.1420. Min Act: -0.1700
Data Index: 5651743 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #19