Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 70 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2588. Min Range: -5.2588
Max Act: 5.2588. Min Act: -0.1700
Data Index: 4504903 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2588. Min Range: -5.2588
Max Act: 5.0713. Min Act: -0.1700
Data Index: 1233925 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2588. Min Range: -5.2588
Max Act: 5.0713. Min Act: -0.1700
Data Index: 4544844 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2588. Min Range: -5.2588
Max Act: 5.0401. Min Act: -0.1700
Data Index: 4893884 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2588. Min Range: -5.2588
Max Act: 5.0088. Min Act: -0.1700
Data Index: 8637914 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2588. Min Range: -5.2588
Max Act: 5.0088. Min Act: -0.1699
Data Index: 3250869 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2588. Min Range: -5.2588
Max Act: 4.9463. Min Act: -0.1700
Data Index: 5685002 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2588. Min Range: -5.2588
Max Act: 4.9776. Min Act: -0.1700
Data Index: 2891127 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2588. Min Range: -5.2588
Max Act: 4.9463. Min Act: -0.1700
Data Index: 1334045 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2588. Min Range: -5.2588
Max Act: 4.9463. Min Act: -0.1700
Data Index: 5943306 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2588. Min Range: -5.2588
Max Act: 4.9463. Min Act: -0.1700
Data Index: 4890481 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2588. Min Range: -5.2588
Max Act: 4.9463. Min Act: -0.1700
Data Index: 11908 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2588. Min Range: -5.2588
Max Act: 4.9463. Min Act: -0.1700
Data Index: 81785 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2588. Min Range: -5.2588
Max Act: 4.9463. Min Act: -0.1700
Data Index: 1649415 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2588. Min Range: -5.2588
Max Act: 4.9151. Min Act: -0.1700
Data Index: 2814142 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2588. Min Range: -5.2588
Max Act: 4.9151. Min Act: -0.1700
Data Index: 1268406 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2588. Min Range: -5.2588
Max Act: 4.9151. Min Act: -0.1700
Data Index: 2193221 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2588. Min Range: -5.2588
Max Act: 4.8838. Min Act: -0.1700
Data Index: 1131085 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2588. Min Range: -5.2588
Max Act: 4.8213. Min Act: -0.1700
Data Index: 7134821 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2588. Min Range: -5.2588
Max Act: 4.7588. Min Act: -0.1700
Data Index: 3528978 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19