Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3882 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8766. Min Range: -5.8766
Max Act: 5.8766. Min Act: -0.1700
Data Index: 5630554 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8766. Min Range: -5.8766
Max Act: 5.8454. Min Act: -0.1700
Data Index: 7139867 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8766. Min Range: -5.8766
Max Act: 5.7829. Min Act: -0.1700
Data Index: 43729 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8766. Min Range: -5.8766
Max Act: 5.7829. Min Act: -0.1700
Data Index: 1033588 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8766. Min Range: -5.8766
Max Act: 5.7516. Min Act: -0.1700
Data Index: 3424318 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8766. Min Range: -5.8766
Max Act: 5.6891. Min Act: -0.1700
Data Index: 8351050 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8766. Min Range: -5.8766
Max Act: 5.5641. Min Act: -0.1700
Data Index: 4151625 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8766. Min Range: -5.8766
Max Act: 5.5641. Min Act: -0.1700
Data Index: 7456971 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8766. Min Range: -5.8766
Max Act: 5.5641. Min Act: -0.1700
Data Index: 3078924 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8766. Min Range: -5.8766
Max Act: 5.4704. Min Act: -0.1700
Data Index: 7879704 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8766. Min Range: -5.8766
Max Act: 5.4704. Min Act: -0.1700
Data Index: 6879004 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8766. Min Range: -5.8766
Max Act: 5.4391. Min Act: -0.1700
Data Index: 4198367 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8766. Min Range: -5.8766
Max Act: 5.4391. Min Act: -0.1700
Data Index: 1293023 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8766. Min Range: -5.8766
Max Act: 5.4079. Min Act: -0.1700
Data Index: 7323495 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8766. Min Range: -5.8766
Max Act: 5.3454. Min Act: -0.1700
Data Index: 2970600 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8766. Min Range: -5.8766
Max Act: 5.3766. Min Act: -0.1700
Data Index: 8698525 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8766. Min Range: -5.8766
Max Act: 5.3766. Min Act: -0.1700
Data Index: 4516831 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8766. Min Range: -5.8766
Max Act: 5.3141. Min Act: -0.1700
Data Index: 5641904 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8766. Min Range: -5.8766
Max Act: 5.3141. Min Act: -0.1700
Data Index: 5158134 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8766. Min Range: -5.8766
Max Act: 5.3454. Min Act: -0.1700
Data Index: 6125142 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19