Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4690 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5043. Min Range: -3.5043
Max Act: 3.5043. Min Act: -0.1700
Data Index: 2319873 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5043. Min Range: -3.5043
Max Act: 3.4730. Min Act: -0.1700
Data Index: 185780 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5043. Min Range: -3.5043
Max Act: 3.3790. Min Act: -0.1700
Data Index: 161476 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5043. Min Range: -3.5043
Max Act: 3.3790. Min Act: -0.1700
Data Index: 7247041 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5043. Min Range: -3.5043
Max Act: 3.3476. Min Act: -0.1700
Data Index: 2891408 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5043. Min Range: -3.5043
Max Act: 3.3476. Min Act: -0.1700
Data Index: 4627351 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5043. Min Range: -3.5043
Max Act: 3.3319. Min Act: -0.1700
Data Index: 2474486 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5043. Min Range: -3.5043
Max Act: 3.3319. Min Act: -0.1700
Data Index: 2122128 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5043. Min Range: -3.5043
Max Act: 3.3162. Min Act: -0.1700
Data Index: 1960501 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5043. Min Range: -3.5043
Max Act: 3.3162. Min Act: -0.1700
Data Index: 7831769 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5043. Min Range: -3.5043
Max Act: 3.3005. Min Act: -0.1700
Data Index: 4395032 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5043. Min Range: -3.5043
Max Act: 3.3005. Min Act: -0.1700
Data Index: 5635798 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5043. Min Range: -3.5043
Max Act: 3.2848. Min Act: -0.1700
Data Index: 8165862 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5043. Min Range: -3.5043
Max Act: 3.2691. Min Act: -0.1700
Data Index: 6817977 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5043. Min Range: -3.5043
Max Act: 3.2691. Min Act: -0.1700
Data Index: 2872657 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5043. Min Range: -3.5043
Max Act: 3.2691. Min Act: -0.1700
Data Index: 7779545 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5043. Min Range: -3.5043
Max Act: 3.2534. Min Act: -0.1700
Data Index: 5447171 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5043. Min Range: -3.5043
Max Act: 3.2534. Min Act: -0.1700
Data Index: 536847 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5043. Min Range: -3.5043
Max Act: 3.2691. Min Act: -0.1700
Data Index: 2340390 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5043. Min Range: -3.5043
Max Act: 3.2534. Min Act: -0.1700
Data Index: 7702663 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #19