Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2515 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4736. Min Range: -5.4736
Max Act: 5.4736. Min Act: -0.1700
Data Index: 3238750 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4736. Min Range: -5.4736
Max Act: 5.3173. Min Act: -0.1700
Data Index: 1148367 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4736. Min Range: -5.4736
Max Act: 5.3173. Min Act: -0.1700
Data Index: 8320209 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4736. Min Range: -5.4736
Max Act: 5.3173. Min Act: -0.1700
Data Index: 3238766 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4736. Min Range: -5.4736
Max Act: 5.2861. Min Act: -0.1700
Data Index: 1560609 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4736. Min Range: -5.4736
Max Act: 5.2548. Min Act: -0.1700
Data Index: 2236601 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4736. Min Range: -5.4736
Max Act: 5.1923. Min Act: -0.1700
Data Index: 1799403 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4736. Min Range: -5.4736
Max Act: 5.1298. Min Act: -0.1700
Data Index: 3271421 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4736. Min Range: -5.4736
Max Act: 5.1298. Min Act: -0.1700
Data Index: 6529794 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4736. Min Range: -5.4736
Max Act: 5.0673. Min Act: -0.1700
Data Index: 6064024 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4736. Min Range: -5.4736
Max Act: 5.0361. Min Act: -0.1700
Data Index: 8096847 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4736. Min Range: -5.4736
Max Act: 5.0673. Min Act: -0.1700
Data Index: 4044705 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4736. Min Range: -5.4736
Max Act: 5.0673. Min Act: -0.1700
Data Index: 114573 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4736. Min Range: -5.4736
Max Act: 5.0361. Min Act: -0.1700
Data Index: 2283643 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4736. Min Range: -5.4736
Max Act: 5.0048. Min Act: -0.1700
Data Index: 5460919 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4736. Min Range: -5.4736
Max Act: 5.0361. Min Act: -0.1700
Data Index: 5281737 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4736. Min Range: -5.4736
Max Act: 5.0048. Min Act: -0.1700
Data Index: 2102207 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4736. Min Range: -5.4736
Max Act: 5.0048. Min Act: -0.1700
Data Index: 8182812 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4736. Min Range: -5.4736
Max Act: 5.0048. Min Act: -0.1700
Data Index: 5743690 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4736. Min Range: -5.4736
Max Act: 5.0048. Min Act: -0.1700
Data Index: 2257444 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #19