Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 363 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3784. Min Range: -4.3784
Max Act: 4.3784. Min Act: -0.1700
Data Index: 426359 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3784. Min Range: -4.3784
Max Act: 4.3784. Min Act: -0.1700
Data Index: 3712693 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3784. Min Range: -4.3784
Max Act: 4.3158. Min Act: -0.1700
Data Index: 5955928 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3784. Min Range: -4.3784
Max Act: 4.2221. Min Act: -0.1700
Data Index: 2152729 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3784. Min Range: -4.3784
Max Act: 4.2533. Min Act: -0.1700
Data Index: 5207022 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3784. Min Range: -4.3784
Max Act: 4.2221. Min Act: -0.1700
Data Index: 8411232 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3784. Min Range: -4.3784
Max Act: 4.1908. Min Act: -0.1700
Data Index: 6963041 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3784. Min Range: -4.3784
Max Act: 4.1908. Min Act: -0.1700
Data Index: 7831147 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3784. Min Range: -4.3784
Max Act: 4.1908. Min Act: -0.1700
Data Index: 5185181 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3784. Min Range: -4.3784
Max Act: 4.1283. Min Act: -0.1700
Data Index: 8659703 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3784. Min Range: -4.3784
Max Act: 4.1596. Min Act: -0.1700
Data Index: 1373804 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3784. Min Range: -4.3784
Max Act: 4.1596. Min Act: -0.1700
Data Index: 7943283 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3784. Min Range: -4.3784
Max Act: 4.1596. Min Act: -0.1700
Data Index: 3232535 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3784. Min Range: -4.3784
Max Act: 4.1283. Min Act: -0.1700
Data Index: 6246960 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3784. Min Range: -4.3784
Max Act: 4.1283. Min Act: -0.1700
Data Index: 5900294 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3784. Min Range: -4.3784
Max Act: 4.0971. Min Act: -0.1700
Data Index: 5456172 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3784. Min Range: -4.3784
Max Act: 4.1283. Min Act: -0.1700
Data Index: 2006264 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3784. Min Range: -4.3784
Max Act: 4.0971. Min Act: -0.1700
Data Index: 1295072 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3784. Min Range: -4.3784
Max Act: 4.0346. Min Act: -0.1700
Data Index: 5996173 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3784. Min Range: -4.3784
Max Act: 4.0971. Min Act: -0.1700
Data Index: 811779 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #19