Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5351 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9229. Min Range: -7.9229
Max Act: 7.9229. Min Act: -0.1700
Data Index: 5522486 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9229. Min Range: -7.9229
Max Act: 7.9229. Min Act: -0.1700
Data Index: 3977221 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9229. Min Range: -7.9229
Max Act: 7.8292. Min Act: -0.1700
Data Index: 6435821 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9229. Min Range: -7.9229
Max Act: 7.8292. Min Act: -0.1700
Data Index: 1735712 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9229. Min Range: -7.9229
Max Act: 7.7667. Min Act: -0.1700
Data Index: 7152614 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9229. Min Range: -7.9229
Max Act: 7.7979. Min Act: -0.1700
Data Index: 7850117 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9229. Min Range: -7.9229
Max Act: 7.7667. Min Act: -0.1700
Data Index: 6292628 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9229. Min Range: -7.9229
Max Act: 7.7042. Min Act: -0.1700
Data Index: 5093931 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9229. Min Range: -7.9229
Max Act: 7.7042. Min Act: -0.1700
Data Index: 2910802 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9229. Min Range: -7.9229
Max Act: 7.6729. Min Act: -0.1700
Data Index: 8599193 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9229. Min Range: -7.9229
Max Act: 7.6729. Min Act: -0.1700
Data Index: 4299844 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9229. Min Range: -7.9229
Max Act: 7.6417. Min Act: -0.1700
Data Index: 1917910 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9229. Min Range: -7.9229
Max Act: 7.6104. Min Act: -0.1700
Data Index: 7815736 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9229. Min Range: -7.9229
Max Act: 7.5479. Min Act: -0.1700
Data Index: 23879 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9229. Min Range: -7.9229
Max Act: 7.5479. Min Act: -0.1700
Data Index: 4491681 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9229. Min Range: -7.9229
Max Act: 7.5167. Min Act: -0.1700
Data Index: 2352590 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9229. Min Range: -7.9229
Max Act: 7.5167. Min Act: -0.1700
Data Index: 1137854 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9229. Min Range: -7.9229
Max Act: 7.5167. Min Act: -0.1700
Data Index: 7923390 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9229. Min Range: -7.9229
Max Act: 7.4854. Min Act: -0.1700
Data Index: 4978780 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9229. Min Range: -7.9229
Max Act: 7.4854. Min Act: -0.1700
Data Index: 1193869 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #19