Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2976 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2238. Min Range: -3.2238
Max Act: 3.2238. Min Act: -0.1700
Data Index: 7133642 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2238. Min Range: -3.2238
Max Act: 3.1609. Min Act: -0.1700
Data Index: 7913301 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2238. Min Range: -3.2238
Max Act: 3.0979. Min Act: -0.1700
Data Index: 3396754 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2238. Min Range: -3.2238
Max Act: 3.0979. Min Act: -0.1700
Data Index: 5379523 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2238. Min Range: -3.2238
Max Act: 2.9874. Min Act: -0.1700
Data Index: 5837272 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2238. Min Range: -3.2238
Max Act: 3.0348. Min Act: -0.1700
Data Index: 8490608 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2238. Min Range: -3.2238
Max Act: 3.0190. Min Act: -0.1700
Data Index: 561559 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2238. Min Range: -3.2238
Max Act: 2.9874. Min Act: -0.1700
Data Index: 2723345 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2238. Min Range: -3.2238
Max Act: 2.9874. Min Act: -0.1700
Data Index: 1794568 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2238. Min Range: -3.2238
Max Act: 2.9716. Min Act: -0.1700
Data Index: 7166710 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2238. Min Range: -3.2238
Max Act: 2.9716. Min Act: -0.1700
Data Index: 3754708 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2238. Min Range: -3.2238
Max Act: 2.9558. Min Act: -0.1700
Data Index: 4334816 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2238. Min Range: -3.2238
Max Act: 2.9558. Min Act: -0.1700
Data Index: 6943899 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2238. Min Range: -3.2238
Max Act: 2.9716. Min Act: -0.1700
Data Index: 6108659 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2238. Min Range: -3.2238
Max Act: 2.9716. Min Act: -0.1700
Data Index: 5004183 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2238. Min Range: -3.2238
Max Act: 2.9558. Min Act: -0.1700
Data Index: 5912773 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2238. Min Range: -3.2238
Max Act: 2.9400. Min Act: -0.1700
Data Index: 5920731 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2238. Min Range: -3.2238
Max Act: 2.9400. Min Act: -0.1700
Data Index: 6142754 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2238. Min Range: -3.2238
Max Act: 2.9241. Min Act: -0.1700
Data Index: 1560954 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2238. Min Range: -3.2238
Max Act: 2.9241. Min Act: -0.1700
Data Index: 6438150 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #19