Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2295 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8670. Min Range: -6.8670
Max Act: 6.8670. Min Act: -0.1700
Data Index: 6030971 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8670. Min Range: -6.8670
Max Act: 6.7733. Min Act: -0.1700
Data Index: 6198720 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8670. Min Range: -6.8670
Max Act: 6.6170. Min Act: -0.1700
Data Index: 4193864 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8670. Min Range: -6.8670
Max Act: 6.5858. Min Act: -0.1700
Data Index: 8164842 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8670. Min Range: -6.8670
Max Act: 6.5233. Min Act: -0.1700
Data Index: 8034571 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8670. Min Range: -6.8670
Max Act: 6.5233. Min Act: -0.1700
Data Index: 2329815 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8670. Min Range: -6.8670
Max Act: 6.5233. Min Act: -0.1700
Data Index: 6684592 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8670. Min Range: -6.8670
Max Act: 6.5233. Min Act: -0.1700
Data Index: 1745631 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8670. Min Range: -6.8670
Max Act: 6.4608. Min Act: -0.1700
Data Index: 6891504 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8670. Min Range: -6.8670
Max Act: 6.4920. Min Act: -0.1700
Data Index: 7969908 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8670. Min Range: -6.8670
Max Act: 6.4608. Min Act: -0.1700
Data Index: 939349 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8670. Min Range: -6.8670
Max Act: 6.4608. Min Act: -0.1700
Data Index: 2172961 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8670. Min Range: -6.8670
Max Act: 6.4608. Min Act: -0.1700
Data Index: 5943150 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8670. Min Range: -6.8670
Max Act: 6.4295. Min Act: -0.1700
Data Index: 4370199 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8670. Min Range: -6.8670
Max Act: 6.4295. Min Act: -0.1700
Data Index: 5015094 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8670. Min Range: -6.8670
Max Act: 6.3670. Min Act: -0.1700
Data Index: 560665 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8670. Min Range: -6.8670
Max Act: 6.3983. Min Act: -0.1700
Data Index: 7264146 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8670. Min Range: -6.8670
Max Act: 6.4295. Min Act: -0.1700
Data Index: 7044112 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8670. Min Range: -6.8670
Max Act: 6.3983. Min Act: -0.1700
Data Index: 6258364 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8670. Min Range: -6.8670
Max Act: 6.3670. Min Act: -0.1700
Data Index: 351205 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #19