Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4418 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9209. Min Range: -4.9209
Max Act: 4.9209. Min Act: -0.1700
Data Index: 8775991 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9209. Min Range: -4.9209
Max Act: 4.9209. Min Act: -0.1700
Data Index: 8396213 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9209. Min Range: -4.9209
Max Act: 4.8271. Min Act: -0.1700
Data Index: 5183737 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9209. Min Range: -4.9209
Max Act: 4.8271. Min Act: -0.1700
Data Index: 4941608 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9209. Min Range: -4.9209
Max Act: 4.7959. Min Act: -0.1700
Data Index: 6184103 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9209. Min Range: -4.9209
Max Act: 4.7646. Min Act: -0.1700
Data Index: 8183683 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9209. Min Range: -4.9209
Max Act: 4.7646. Min Act: -0.1700
Data Index: 6273884 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9209. Min Range: -4.9209
Max Act: 4.7334. Min Act: -0.1700
Data Index: 1384801 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9209. Min Range: -4.9209
Max Act: 4.7334. Min Act: -0.1700
Data Index: 5916939 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9209. Min Range: -4.9209
Max Act: 4.7021. Min Act: -0.1700
Data Index: 1285295 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9209. Min Range: -4.9209
Max Act: 4.7334. Min Act: -0.1700
Data Index: 1167441 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9209. Min Range: -4.9209
Max Act: 4.6709. Min Act: -0.1700
Data Index: 4648896 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9209. Min Range: -4.9209
Max Act: 4.6396. Min Act: -0.1700
Data Index: 245769 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9209. Min Range: -4.9209
Max Act: 4.6396. Min Act: -0.1700
Data Index: 3942289 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9209. Min Range: -4.9209
Max Act: 4.6084. Min Act: -0.1700
Data Index: 8592256 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9209. Min Range: -4.9209
Max Act: 4.6396. Min Act: -0.1700
Data Index: 659695 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9209. Min Range: -4.9209
Max Act: 4.6396. Min Act: -0.1700
Data Index: 458570 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9209. Min Range: -4.9209
Max Act: 4.6084. Min Act: -0.1700
Data Index: 72879 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9209. Min Range: -4.9209
Max Act: 4.5771. Min Act: -0.1700
Data Index: 6278801 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9209. Min Range: -4.9209
Max Act: 4.6084. Min Act: -0.1700
Data Index: 1953185 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19