Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1694 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0789. Min Range: -5.0789
Max Act: 5.0789. Min Act: -0.1700
Data Index: 2709039 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0789. Min Range: -5.0789
Max Act: 5.0476. Min Act: -0.1700
Data Index: 145677 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0789. Min Range: -5.0789
Max Act: 4.9851. Min Act: -0.1700
Data Index: 2602301 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0789. Min Range: -5.0789
Max Act: 4.9226. Min Act: -0.1700
Data Index: 3023435 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0789. Min Range: -5.0789
Max Act: 4.8288. Min Act: -0.1700
Data Index: 3356029 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0789. Min Range: -5.0789
Max Act: 4.8288. Min Act: -0.1700
Data Index: 6921729 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0789. Min Range: -5.0789
Max Act: 4.7351. Min Act: -0.1700
Data Index: 1565427 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0789. Min Range: -5.0789
Max Act: 4.7663. Min Act: -0.1700
Data Index: 7153188 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0789. Min Range: -5.0789
Max Act: 4.7663. Min Act: -0.1700
Data Index: 3166192 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0789. Min Range: -5.0789
Max Act: 4.7351. Min Act: -0.1700
Data Index: 1473827 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0789. Min Range: -5.0789
Max Act: 4.7663. Min Act: -0.1700
Data Index: 607078 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0789. Min Range: -5.0789
Max Act: 4.7351. Min Act: -0.1700
Data Index: 605167 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0789. Min Range: -5.0789
Max Act: 4.7351. Min Act: -0.1700
Data Index: 5821930 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0789. Min Range: -5.0789
Max Act: 4.7663. Min Act: -0.1700
Data Index: 6532739 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0789. Min Range: -5.0789
Max Act: 4.7351. Min Act: -0.1700
Data Index: 71631 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0789. Min Range: -5.0789
Max Act: 4.7038. Min Act: -0.1700
Data Index: 3324161 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0789. Min Range: -5.0789
Max Act: 4.7038. Min Act: -0.1700
Data Index: 6665192 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0789. Min Range: -5.0789
Max Act: 4.6413. Min Act: -0.1700
Data Index: 4696943 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0789. Min Range: -5.0789
Max Act: 4.6726. Min Act: -0.1700
Data Index: 4040786 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0789. Min Range: -5.0789
Max Act: 4.6726. Min Act: -0.1700
Data Index: 3322544 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #19