Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3488 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1533. Min Range: -7.1533
Max Act: 7.1533. Min Act: -0.1700
Data Index: 6309576 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1533. Min Range: -7.1533
Max Act: 7.0283. Min Act: -0.1700
Data Index: 399032 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1533. Min Range: -7.1533
Max Act: 7.0283. Min Act: -0.1700
Data Index: 5695371 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1533. Min Range: -7.1533
Max Act: 6.9970. Min Act: -0.1700
Data Index: 6823529 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1533. Min Range: -7.1533
Max Act: 6.9345. Min Act: -0.1700
Data Index: 7455935 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1533. Min Range: -7.1533
Max Act: 6.9345. Min Act: -0.1700
Data Index: 5500176 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1533. Min Range: -7.1533
Max Act: 6.9033. Min Act: -0.1700
Data Index: 6182528 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1533. Min Range: -7.1533
Max Act: 6.8720. Min Act: -0.1700
Data Index: 2910167 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1533. Min Range: -7.1533
Max Act: 6.8720. Min Act: -0.1700
Data Index: 2649730 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1533. Min Range: -7.1533
Max Act: 6.8095. Min Act: -0.1700
Data Index: 3277003 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1533. Min Range: -7.1533
Max Act: 6.8095. Min Act: -0.1700
Data Index: 7234398 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1533. Min Range: -7.1533
Max Act: 6.8095. Min Act: -0.1700
Data Index: 1980796 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1533. Min Range: -7.1533
Max Act: 6.8095. Min Act: -0.1700
Data Index: 6577645 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1533. Min Range: -7.1533
Max Act: 6.8095. Min Act: -0.1700
Data Index: 1050016 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1533. Min Range: -7.1533
Max Act: 6.7783. Min Act: -0.1700
Data Index: 1821433 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1533. Min Range: -7.1533
Max Act: 6.7783. Min Act: -0.1700
Data Index: 4190323 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1533. Min Range: -7.1533
Max Act: 6.7470. Min Act: -0.1700
Data Index: 5763792 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1533. Min Range: -7.1533
Max Act: 6.7470. Min Act: -0.1700
Data Index: 1655137 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1533. Min Range: -7.1533
Max Act: 6.7158. Min Act: -0.1700
Data Index: 7688358 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1533. Min Range: -7.1533
Max Act: 6.7158. Min Act: -0.1700
Data Index: 875662 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19