Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2865 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1167. Min Range: -5.1167
Max Act: 5.1167. Min Act: -0.1700
Data Index: 8736683 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1167. Min Range: -5.1167
Max Act: 4.9292. Min Act: -0.1700
Data Index: 6952252 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1167. Min Range: -5.1167
Max Act: 4.8354. Min Act: -0.1700
Data Index: 3707744 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1167. Min Range: -5.1167
Max Act: 4.8042. Min Act: -0.1700
Data Index: 3771451 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1167. Min Range: -5.1167
Max Act: 4.7417. Min Act: -0.1700
Data Index: 6697937 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1167. Min Range: -5.1167
Max Act: 4.7729. Min Act: -0.1700
Data Index: 6539660 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1167. Min Range: -5.1167
Max Act: 4.7417. Min Act: -0.1700
Data Index: 6655615 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1167. Min Range: -5.1167
Max Act: 4.7729. Min Act: -0.1700
Data Index: 2039832 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1167. Min Range: -5.1167
Max Act: 4.7104. Min Act: -0.1700
Data Index: 4113104 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1167. Min Range: -5.1167
Max Act: 4.6792. Min Act: -0.1700
Data Index: 8607513 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1167. Min Range: -5.1167
Max Act: 4.6479. Min Act: -0.1700
Data Index: 123819 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1167. Min Range: -5.1167
Max Act: 4.6479. Min Act: -0.1700
Data Index: 7635953 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1167. Min Range: -5.1167
Max Act: 4.6479. Min Act: -0.1700
Data Index: 214300 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1167. Min Range: -5.1167
Max Act: 4.6167. Min Act: -0.1700
Data Index: 875206 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1167. Min Range: -5.1167
Max Act: 4.6167. Min Act: -0.1700
Data Index: 826544 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1167. Min Range: -5.1167
Max Act: 4.6167. Min Act: -0.1700
Data Index: 5105363 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1167. Min Range: -5.1167
Max Act: 4.6167. Min Act: -0.1700
Data Index: 6872392 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1167. Min Range: -5.1167
Max Act: 4.5854. Min Act: -0.1700
Data Index: 2212225 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1167. Min Range: -5.1167
Max Act: 4.5854. Min Act: -0.1700
Data Index: 4156614 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1167. Min Range: -5.1167
Max Act: 4.5542. Min Act: -0.1700
Data Index: 8102987 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19