Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6313 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3629. Min Range: -6.3629
Max Act: 6.3629. Min Act: -0.1700
Data Index: 381132 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3629. Min Range: -6.3629
Max Act: 6.1441. Min Act: -0.1700
Data Index: 1903049 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3629. Min Range: -6.3629
Max Act: 6.0504. Min Act: -0.1700
Data Index: 4154042 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3629. Min Range: -6.3629
Max Act: 6.0504. Min Act: -0.1700
Data Index: 2055485 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3629. Min Range: -6.3629
Max Act: 6.0504. Min Act: -0.1700
Data Index: 7714492 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3629. Min Range: -6.3629
Max Act: 6.0504. Min Act: -0.1700
Data Index: 421187 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3629. Min Range: -6.3629
Max Act: 6.0191. Min Act: -0.1700
Data Index: 4347669 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3629. Min Range: -6.3629
Max Act: 6.0191. Min Act: -0.1700
Data Index: 509101 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3629. Min Range: -6.3629
Max Act: 5.9879. Min Act: -0.1700
Data Index: 3322980 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3629. Min Range: -6.3629
Max Act: 5.9879. Min Act: -0.1700
Data Index: 1402827 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3629. Min Range: -6.3629
Max Act: 5.9566. Min Act: -0.1700
Data Index: 2202380 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3629. Min Range: -6.3629
Max Act: 5.9566. Min Act: -0.1700
Data Index: 2006298 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3629. Min Range: -6.3629
Max Act: 5.9566. Min Act: -0.1700
Data Index: 4560137 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3629. Min Range: -6.3629
Max Act: 5.9566. Min Act: -0.1700
Data Index: 106626 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3629. Min Range: -6.3629
Max Act: 5.9566. Min Act: -0.1700
Data Index: 3918624 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3629. Min Range: -6.3629
Max Act: 5.9566. Min Act: -0.1700
Data Index: 7265843 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3629. Min Range: -6.3629
Max Act: 5.9566. Min Act: -0.1700
Data Index: 5189607 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3629. Min Range: -6.3629
Max Act: 5.9254. Min Act: -0.1700
Data Index: 1857696 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3629. Min Range: -6.3629
Max Act: 5.9254. Min Act: -0.1700
Data Index: 7136498 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3629. Min Range: -6.3629
Max Act: 5.9254. Min Act: -0.1700
Data Index: 3833554 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19