Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3850 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7533. Min Range: -3.7533
Max Act: 3.7533. Min Act: -0.1700
Data Index: 275894 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7533. Min Range: -3.7533
Max Act: 3.7220. Min Act: -0.1700
Data Index: 275893 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7533. Min Range: -3.7533
Max Act: 3.6281. Min Act: -0.1700
Data Index: 2694118 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7533. Min Range: -3.7533
Max Act: 3.6281. Min Act: -0.1700
Data Index: 1646977 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7533. Min Range: -3.7533
Max Act: 3.5655. Min Act: -0.1700
Data Index: 3310426 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7533. Min Range: -3.7533
Max Act: 3.5342. Min Act: -0.1700
Data Index: 300035 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7533. Min Range: -3.7533
Max Act: 3.5029. Min Act: -0.1700
Data Index: 7712425 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7533. Min Range: -3.7533
Max Act: 3.5655. Min Act: -0.1700
Data Index: 3873245 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7533. Min Range: -3.7533
Max Act: 3.5029. Min Act: -0.1700
Data Index: 708566 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7533. Min Range: -3.7533
Max Act: 3.5029. Min Act: -0.1700
Data Index: 3873246 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7533. Min Range: -3.7533
Max Act: 3.4715. Min Act: -0.1700
Data Index: 3134374 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7533. Min Range: -3.7533
Max Act: 3.5029. Min Act: -0.1700
Data Index: 3310425 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7533. Min Range: -3.7533
Max Act: 3.4715. Min Act: -0.1700
Data Index: 7007377 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7533. Min Range: -3.7533
Max Act: 3.4715. Min Act: -0.1700
Data Index: 582291 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7533. Min Range: -3.7533
Max Act: 3.4715. Min Act: -0.1700
Data Index: 857491 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7533. Min Range: -3.7533
Max Act: 3.4089. Min Act: -0.1700
Data Index: 4930765 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7533. Min Range: -3.7533
Max Act: 3.4089. Min Act: -0.1700
Data Index: 3026953 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7533. Min Range: -3.7533
Max Act: 3.3775. Min Act: -0.1700
Data Index: 8653252 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7533. Min Range: -3.7533
Max Act: 3.3618. Min Act: -0.1700
Data Index: 854473 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7533. Min Range: -3.7533
Max Act: 3.3461. Min Act: -0.1700
Data Index: 2392747 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19