Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3242 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7412. Min Range: -7.7412
Max Act: 7.7412. Min Act: -0.1700
Data Index: 2211705 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7412. Min Range: -7.7412
Max Act: 7.0849. Min Act: -0.1700
Data Index: 3701607 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7412. Min Range: -7.7412
Max Act: 7.0537. Min Act: -0.1700
Data Index: 2666587 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7412. Min Range: -7.7412
Max Act: 7.0849. Min Act: -0.1700
Data Index: 3701599 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7412. Min Range: -7.7412
Max Act: 7.0224. Min Act: -0.1700
Data Index: 3353805 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7412. Min Range: -7.7412
Max Act: 6.9912. Min Act: -0.1700
Data Index: 2890933 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7412. Min Range: -7.7412
Max Act: 6.9287. Min Act: -0.1700
Data Index: 3843889 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7412. Min Range: -7.7412
Max Act: 6.8974. Min Act: -0.1700
Data Index: 3701602 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7412. Min Range: -7.7412
Max Act: 6.8662. Min Act: -0.1700
Data Index: 545750 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7412. Min Range: -7.7412
Max Act: 6.8662. Min Act: -0.1700
Data Index: 1018944 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7412. Min Range: -7.7412
Max Act: 6.8662. Min Act: -0.1700
Data Index: 3996253 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7412. Min Range: -7.7412
Max Act: 6.7724. Min Act: -0.1700
Data Index: 4100417 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7412. Min Range: -7.7412
Max Act: 6.7412. Min Act: -0.1700
Data Index: 720642 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7412. Min Range: -7.7412
Max Act: 6.7724. Min Act: -0.1700
Data Index: 3701604 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7412. Min Range: -7.7412
Max Act: 6.7412. Min Act: -0.1700
Data Index: 4179961 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7412. Min Range: -7.7412
Max Act: 6.7099. Min Act: -0.1700
Data Index: 8701638 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7412. Min Range: -7.7412
Max Act: 6.7099. Min Act: -0.1700
Data Index: 4596633 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7412. Min Range: -7.7412
Max Act: 6.6787. Min Act: -0.1700
Data Index: 4075818 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7412. Min Range: -7.7412
Max Act: 6.6787. Min Act: -0.1700
Data Index: 2201906 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7412. Min Range: -7.7412
Max Act: 6.6474. Min Act: -0.1700
Data Index: 3996252 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #19