Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3427 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3099. Min Range: -6.3099
Max Act: 6.3099. Min Act: -0.1700
Data Index: 1890607 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3099. Min Range: -6.3099
Max Act: 6.2474. Min Act: -0.1700
Data Index: 1129939 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3099. Min Range: -6.3099
Max Act: 6.1849. Min Act: -0.1700
Data Index: 8486305 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3099. Min Range: -6.3099
Max Act: 6.0912. Min Act: -0.1700
Data Index: 1833586 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3099. Min Range: -6.3099
Max Act: 6.0287. Min Act: -0.1700
Data Index: 8087784 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3099. Min Range: -6.3099
Max Act: 6.0599. Min Act: -0.1700
Data Index: 1474764 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3099. Min Range: -6.3099
Max Act: 6.0287. Min Act: -0.1700
Data Index: 5605381 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3099. Min Range: -6.3099
Max Act: 5.9974. Min Act: -0.1700
Data Index: 5773384 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3099. Min Range: -6.3099
Max Act: 5.9974. Min Act: -0.1700
Data Index: 2527775 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3099. Min Range: -6.3099
Max Act: 5.9974. Min Act: -0.1700
Data Index: 4621846 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3099. Min Range: -6.3099
Max Act: 5.9974. Min Act: -0.1700
Data Index: 7399791 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3099. Min Range: -6.3099
Max Act: 5.9974. Min Act: -0.1700
Data Index: 2254504 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3099. Min Range: -6.3099
Max Act: 5.9662. Min Act: -0.1700
Data Index: 5874292 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3099. Min Range: -6.3099
Max Act: 5.9662. Min Act: -0.1700
Data Index: 6930812 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3099. Min Range: -6.3099
Max Act: 5.9662. Min Act: -0.1700
Data Index: 157074 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3099. Min Range: -6.3099
Max Act: 5.9662. Min Act: -0.1700
Data Index: 3846914 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3099. Min Range: -6.3099
Max Act: 5.9349. Min Act: -0.1700
Data Index: 4199629 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3099. Min Range: -6.3099
Max Act: 5.9662. Min Act: -0.1700
Data Index: 7149940 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3099. Min Range: -6.3099
Max Act: 5.9662. Min Act: -0.1700
Data Index: 7382268 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3099. Min Range: -6.3099
Max Act: 5.9662. Min Act: -0.1700
Data Index: 26790 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #19