Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2633 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4542. Min Range: -3.4542
Max Act: 3.4542. Min Act: -0.1700
Data Index: 3649157 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4542. Min Range: -3.4542
Max Act: 3.3131. Min Act: -0.1700
Data Index: 3637808 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4542. Min Range: -3.4542
Max Act: 3.2660. Min Act: -0.1700
Data Index: 6718837 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4542. Min Range: -3.4542
Max Act: 3.2503. Min Act: -0.1700
Data Index: 2283039 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4542. Min Range: -3.4542
Max Act: 3.2503. Min Act: -0.1700
Data Index: 3936608 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4542. Min Range: -3.4542
Max Act: 3.2660. Min Act: -0.1700
Data Index: 5542578 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4542. Min Range: -3.4542
Max Act: 3.2346. Min Act: -0.1700
Data Index: 8511451 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4542. Min Range: -3.4542
Max Act: 3.2503. Min Act: -0.1700
Data Index: 3743260 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4542. Min Range: -3.4542
Max Act: 3.2346. Min Act: -0.1700
Data Index: 5284643 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4542. Min Range: -3.4542
Max Act: 3.2189. Min Act: -0.1700
Data Index: 4761896 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4542. Min Range: -3.4542
Max Act: 3.2189. Min Act: -0.1700
Data Index: 7333729 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4542. Min Range: -3.4542
Max Act: 3.2031. Min Act: -0.1700
Data Index: 3500773 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4542. Min Range: -3.4542
Max Act: 3.1874. Min Act: -0.1700
Data Index: 1941280 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4542. Min Range: -3.4542
Max Act: 3.1874. Min Act: -0.1700
Data Index: 130379 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4542. Min Range: -3.4542
Max Act: 3.1874. Min Act: -0.1700
Data Index: 1901902 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4542. Min Range: -3.4542
Max Act: 3.1717. Min Act: -0.1700
Data Index: 243688 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4542. Min Range: -3.4542
Max Act: 3.1559. Min Act: -0.1700
Data Index: 6015187 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4542. Min Range: -3.4542
Max Act: 3.1717. Min Act: -0.1700
Data Index: 5474407 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4542. Min Range: -3.4542
Max Act: 3.1717. Min Act: -0.1700
Data Index: 1504470 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4542. Min Range: -3.4542
Max Act: 3.1717. Min Act: -0.1700
Data Index: 803713 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19