Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 667 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4567. Min Range: -5.4567
Max Act: 5.4567. Min Act: -0.1700
Data Index: 1531210 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4567. Min Range: -5.4567
Max Act: 5.3630. Min Act: -0.1700
Data Index: 1065300 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4567. Min Range: -5.4567
Max Act: 5.2067. Min Act: -0.1700
Data Index: 8031559 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4567. Min Range: -5.4567
Max Act: 5.1755. Min Act: -0.1700
Data Index: 4263049 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4567. Min Range: -5.4567
Max Act: 5.0817. Min Act: -0.1700
Data Index: 3290366 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4567. Min Range: -5.4567
Max Act: 5.0505. Min Act: -0.1700
Data Index: 6599810 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4567. Min Range: -5.4567
Max Act: 5.0817. Min Act: -0.1700
Data Index: 3628316 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4567. Min Range: -5.4567
Max Act: 5.0192. Min Act: -0.1700
Data Index: 983806 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4567. Min Range: -5.4567
Max Act: 5.0505. Min Act: -0.1700
Data Index: 923660 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4567. Min Range: -5.4567
Max Act: 5.0192. Min Act: -0.1700
Data Index: 8259154 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4567. Min Range: -5.4567
Max Act: 4.9880. Min Act: -0.1700
Data Index: 7411899 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4567. Min Range: -5.4567
Max Act: 4.9567. Min Act: -0.1700
Data Index: 8335854 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4567. Min Range: -5.4567
Max Act: 4.9880. Min Act: -0.1700
Data Index: 3126279 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4567. Min Range: -5.4567
Max Act: 4.9567. Min Act: -0.1700
Data Index: 2355016 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4567. Min Range: -5.4567
Max Act: 4.9567. Min Act: -0.1700
Data Index: 4329534 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4567. Min Range: -5.4567
Max Act: 4.9255. Min Act: -0.1700
Data Index: 6274692 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4567. Min Range: -5.4567
Max Act: 4.9880. Min Act: -0.1700
Data Index: 1741439 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4567. Min Range: -5.4567
Max Act: 4.9567. Min Act: -0.1700
Data Index: 5280205 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4567. Min Range: -5.4567
Max Act: 4.9567. Min Act: -0.1700
Data Index: 144318 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4567. Min Range: -5.4567
Max Act: 4.9567. Min Act: -0.1700
Data Index: 6061813 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19