Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1914 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8231. Min Range: -4.8231
Max Act: 4.8231. Min Act: -0.1700
Data Index: 1912350 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8231. Min Range: -4.8231
Max Act: 4.7606. Min Act: -0.1700
Data Index: 2994454 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8231. Min Range: -4.8231
Max Act: 4.7294. Min Act: -0.1700
Data Index: 2820998 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8231. Min Range: -4.8231
Max Act: 4.7294. Min Act: -0.1700
Data Index: 7450309 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8231. Min Range: -4.8231
Max Act: 4.6669. Min Act: -0.1700
Data Index: 1565666 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8231. Min Range: -4.8231
Max Act: 4.6669. Min Act: -0.1700
Data Index: 2237797 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8231. Min Range: -4.8231
Max Act: 4.6669. Min Act: -0.1700
Data Index: 1634508 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8231. Min Range: -4.8231
Max Act: 4.6669. Min Act: -0.1700
Data Index: 81923 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8231. Min Range: -4.8231
Max Act: 4.6669. Min Act: -0.1700
Data Index: 8322235 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8231. Min Range: -4.8231
Max Act: 4.6669. Min Act: -0.1700
Data Index: 8765837 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8231. Min Range: -4.8231
Max Act: 4.6669. Min Act: -0.1700
Data Index: 3652803 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8231. Min Range: -4.8231
Max Act: 4.6669. Min Act: -0.1700
Data Index: 176780 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8231. Min Range: -4.8231
Max Act: 4.6356. Min Act: -0.1700
Data Index: 4957285 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8231. Min Range: -4.8231
Max Act: 4.6356. Min Act: -0.1700
Data Index: 2672722 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8231. Min Range: -4.8231
Max Act: 4.6356. Min Act: -0.1700
Data Index: 525022 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8231. Min Range: -4.8231
Max Act: 4.6356. Min Act: -0.1700
Data Index: 5131115 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8231. Min Range: -4.8231
Max Act: 4.6356. Min Act: -0.1700
Data Index: 4119734 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8231. Min Range: -4.8231
Max Act: 4.6356. Min Act: -0.1700
Data Index: 4812662 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8231. Min Range: -4.8231
Max Act: 4.6356. Min Act: -0.1700
Data Index: 4147078 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8231. Min Range: -4.8231
Max Act: 4.6356. Min Act: -0.1700
Data Index: 3768838 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19