Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1746 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0588. Min Range: -7.0588
Max Act: 7.0588. Min Act: -0.1700
Data Index: 6334629 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0588. Min Range: -7.0588
Max Act: 6.8088. Min Act: -0.1700
Data Index: 2956653 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0588. Min Range: -7.0588
Max Act: 6.7775. Min Act: -0.1700
Data Index: 8247625 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0588. Min Range: -7.0588
Max Act: 6.6838. Min Act: -0.1700
Data Index: 4897300 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0588. Min Range: -7.0588
Max Act: 6.6525. Min Act: -0.1700
Data Index: 224048 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0588. Min Range: -7.0588
Max Act: 6.6213. Min Act: -0.1700
Data Index: 518396 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0588. Min Range: -7.0588
Max Act: 6.5275. Min Act: -0.1700
Data Index: 7262971 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0588. Min Range: -7.0588
Max Act: 6.5588. Min Act: -0.1700
Data Index: 7787385 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0588. Min Range: -7.0588
Max Act: 6.5588. Min Act: -0.1700
Data Index: 2114263 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0588. Min Range: -7.0588
Max Act: 6.5588. Min Act: -0.1700
Data Index: 1598424 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0588. Min Range: -7.0588
Max Act: 6.5275. Min Act: -0.1700
Data Index: 385197 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0588. Min Range: -7.0588
Max Act: 6.4963. Min Act: -0.1700
Data Index: 1746495 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0588. Min Range: -7.0588
Max Act: 6.4650. Min Act: -0.1700
Data Index: 7345238 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0588. Min Range: -7.0588
Max Act: 6.4338. Min Act: -0.1700
Data Index: 4008403 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0588. Min Range: -7.0588
Max Act: 6.4650. Min Act: -0.1700
Data Index: 1997186 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0588. Min Range: -7.0588
Max Act: 6.3713. Min Act: -0.1700
Data Index: 88421 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0588. Min Range: -7.0588
Max Act: 6.4025. Min Act: -0.1700
Data Index: 534777 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0588. Min Range: -7.0588
Max Act: 6.4025. Min Act: -0.1700
Data Index: 4129644 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0588. Min Range: -7.0588
Max Act: 6.4025. Min Act: -0.1700
Data Index: 3623391 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0588. Min Range: -7.0588
Max Act: 6.4025. Min Act: -0.1700
Data Index: 830084 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19