Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2689 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9488. Min Range: -4.9488
Max Act: 4.9488. Min Act: -0.1700
Data Index: 1838682 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9488. Min Range: -4.9488
Max Act: 4.8863. Min Act: -0.1700
Data Index: 3098683 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9488. Min Range: -4.9488
Max Act: 4.8551. Min Act: -0.1700
Data Index: 4182044 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9488. Min Range: -4.9488
Max Act: 4.8863. Min Act: -0.1700
Data Index: 5141984 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9488. Min Range: -4.9488
Max Act: 4.8551. Min Act: -0.1700
Data Index: 5141978 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9488. Min Range: -4.9488
Max Act: 4.8551. Min Act: -0.1700
Data Index: 6932901 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9488. Min Range: -4.9488
Max Act: 4.8238. Min Act: -0.1700
Data Index: 6273332 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9488. Min Range: -4.9488
Max Act: 4.7926. Min Act: -0.1700
Data Index: 1100951 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9488. Min Range: -4.9488
Max Act: 4.7926. Min Act: -0.1700
Data Index: 6273324 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9488. Min Range: -4.9488
Max Act: 4.7926. Min Act: -0.1700
Data Index: 1724888 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9488. Min Range: -4.9488
Max Act: 4.7926. Min Act: -0.1700
Data Index: 3449061 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9488. Min Range: -4.9488
Max Act: 4.7613. Min Act: -0.1700
Data Index: 6357113 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9488. Min Range: -4.9488
Max Act: 4.7613. Min Act: -0.1700
Data Index: 4007308 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9488. Min Range: -4.9488
Max Act: 4.7613. Min Act: -0.1700
Data Index: 8074417 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9488. Min Range: -4.9488
Max Act: 4.6988. Min Act: -0.1700
Data Index: 3952277 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9488. Min Range: -4.9488
Max Act: 4.7301. Min Act: -0.1700
Data Index: 4681179 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9488. Min Range: -4.9488
Max Act: 4.6988. Min Act: -0.1700
Data Index: 251068 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9488. Min Range: -4.9488
Max Act: 4.6988. Min Act: -0.1700
Data Index: 944408 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9488. Min Range: -4.9488
Max Act: 4.7301. Min Act: -0.1700
Data Index: 7116903 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9488. Min Range: -4.9488
Max Act: 4.6988. Min Act: -0.1700
Data Index: 5055000 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #19