Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1258 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1474. Min Range: -3.1474
Max Act: 3.1474. Min Act: -0.1700
Data Index: 833970 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1474. Min Range: -3.1474
Max Act: 3.1316. Min Act: -0.1700
Data Index: 4049639 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1474. Min Range: -3.1474
Max Act: 3.0844. Min Act: -0.1700
Data Index: 4987770 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1474. Min Range: -3.1474
Max Act: 3.0528. Min Act: -0.1700
Data Index: 2932804 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1474. Min Range: -3.1474
Max Act: 3.0212. Min Act: -0.1700
Data Index: 4017962 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1474. Min Range: -3.1474
Max Act: 3.0370. Min Act: -0.1700
Data Index: 7498759 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1474. Min Range: -3.1474
Max Act: 3.0370. Min Act: -0.1700
Data Index: 467571 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1474. Min Range: -3.1474
Max Act: 3.0528. Min Act: -0.1700
Data Index: 2709196 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1474. Min Range: -3.1474
Max Act: 2.9738. Min Act: -0.1700
Data Index: 5697213 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1474. Min Range: -3.1474
Max Act: 2.9896. Min Act: -0.1700
Data Index: 4037358 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1474. Min Range: -3.1474
Max Act: 2.9738. Min Act: -0.1700
Data Index: 3042566 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1474. Min Range: -3.1474
Max Act: 2.9896. Min Act: -0.1700
Data Index: 4451427 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1474. Min Range: -3.1474
Max Act: 2.9896. Min Act: -0.1700
Data Index: 6342592 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1474. Min Range: -3.1474
Max Act: 2.9738. Min Act: -0.1700
Data Index: 1836858 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1474. Min Range: -3.1474
Max Act: 2.9263. Min Act: -0.1700
Data Index: 5938336 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1474. Min Range: -3.1474
Max Act: 2.9422. Min Act: -0.1700
Data Index: 3419555 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1474. Min Range: -3.1474
Max Act: 2.9263. Min Act: -0.1700
Data Index: 1046631 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1474. Min Range: -3.1474
Max Act: 2.9422. Min Act: -0.1700
Data Index: 5921567 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1474. Min Range: -3.1474
Max Act: 2.9422. Min Act: -0.1700
Data Index: 1644498 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1474. Min Range: -3.1474
Max Act: 2.8946. Min Act: -0.1700
Data Index: 7609138 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #19