Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1278 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7203. Min Range: -5.7203
Max Act: 5.7203. Min Act: -0.1700
Data Index: 4218799 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7203. Min Range: -5.7203
Max Act: 5.7203. Min Act: -0.1700
Data Index: 666048 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7203. Min Range: -5.7203
Max Act: 5.6891. Min Act: -0.1700
Data Index: 178072 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7203. Min Range: -5.7203
Max Act: 5.6578. Min Act: -0.1700
Data Index: 6141476 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7203. Min Range: -5.7203
Max Act: 5.5953. Min Act: -0.1700
Data Index: 8328405 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7203. Min Range: -5.7203
Max Act: 5.6266. Min Act: -0.1700
Data Index: 8189244 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7203. Min Range: -5.7203
Max Act: 5.5953. Min Act: -0.1700
Data Index: 1101745 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7203. Min Range: -5.7203
Max Act: 5.6266. Min Act: -0.1700
Data Index: 8144879 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7203. Min Range: -5.7203
Max Act: 5.5953. Min Act: -0.1700
Data Index: 8073760 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7203. Min Range: -5.7203
Max Act: 5.5641. Min Act: -0.1700
Data Index: 5401226 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7203. Min Range: -5.7203
Max Act: 5.5641. Min Act: -0.1700
Data Index: 1659589 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7203. Min Range: -5.7203
Max Act: 5.5641. Min Act: -0.1700
Data Index: 335016 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7203. Min Range: -5.7203
Max Act: 5.5641. Min Act: -0.1700
Data Index: 4610065 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7203. Min Range: -5.7203
Max Act: 5.5328. Min Act: -0.1700
Data Index: 5290000 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7203. Min Range: -5.7203
Max Act: 5.5328. Min Act: -0.1700
Data Index: 4762783 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7203. Min Range: -5.7203
Max Act: 5.5328. Min Act: -0.1700
Data Index: 2774134 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7203. Min Range: -5.7203
Max Act: 5.5641. Min Act: -0.1700
Data Index: 187095 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7203. Min Range: -5.7203
Max Act: 5.5328. Min Act: -0.1700
Data Index: 312335 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7203. Min Range: -5.7203
Max Act: 5.5016. Min Act: -0.1700
Data Index: 4549175 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7203. Min Range: -5.7203
Max Act: 5.5328. Min Act: -0.1700
Data Index: 6134421 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #19