Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2579 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.9993. Min Act: -0.1700
Data Index: 6712371 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.9368. Min Act: -0.1700
Data Index: 6589909 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.9056. Min Act: -0.1700
Data Index: 206051 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.9368. Min Act: -0.1700
Data Index: 3985282 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.9056. Min Act: -0.1700
Data Index: 7329714 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.9056. Min Act: -0.1700
Data Index: 2174089 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.8743. Min Act: -0.1700
Data Index: 5055436 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.7806. Min Act: -0.1700
Data Index: 7479431 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.7493. Min Act: -0.1700
Data Index: 3067247 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.7181. Min Act: -0.1700
Data Index: 6551398 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.7181. Min Act: -0.1700
Data Index: 2264480 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.7181. Min Act: -0.1700
Data Index: 8758103 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.6556. Min Act: -0.1700
Data Index: 2508241 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.6868. Min Act: -0.1700
Data Index: 4167666 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.6868. Min Act: -0.1700
Data Index: 6727445 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.6556. Min Act: -0.1700
Data Index: 5553787 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.6556. Min Act: -0.1700
Data Index: 6885393 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.6868. Min Act: -0.1700
Data Index: 3615565 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.6556. Min Act: -0.1700
Data Index: 5184888 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9993. Min Range: -5.9993
Max Act: 5.6556. Min Act: -0.1700
Data Index: 2468018 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #19