Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2431 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.7063. Min Range: -2.7063
Max Act: 2.7063. Min Act: -0.0001
Data Index: 650244 (C4 (Web Text))
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7063. Min Range: -2.7063
Max Act: 2.6980. Min Act: -0.0001
Data Index: 314382 (C4 (Web Text))
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7063. Min Range: -2.7063
Max Act: 2.5286. Min Act: -0.0001
Data Index: 597085 (C4 (Web Text))
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7063. Min Range: -2.7063
Max Act: 2.5308. Min Act: -0.0000
Data Index: 159627 (C4 (Web Text))
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7063. Min Range: -2.7063
Max Act: 2.3052. Min Act: -0.0001
Data Index: 273684 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7063. Min Range: -2.7063
Max Act: 2.4557. Min Act: -0.0001
Data Index: 299870 (C4 (Web Text))
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7063. Min Range: -2.7063
Max Act: 2.3412. Min Act: -0.0001
Data Index: 803650 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7063. Min Range: -2.7063
Max Act: 2.2783. Min Act: -0.0001
Data Index: 662930 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7063. Min Range: -2.7063
Max Act: 2.1355. Min Act: -0.0001
Data Index: 184545 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7063. Min Range: -2.7063
Max Act: 2.2480. Min Act: -0.0001
Data Index: 185933 (C4 (Web Text))
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7063. Min Range: -2.7063
Max Act: 2.0836. Min Act: -0.0001
Data Index: 128842 (C4 (Web Text))
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7063. Min Range: -2.7063
Max Act: 2.1393. Min Act: -0.0001
Data Index: 980036 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7063. Min Range: -2.7063
Max Act: 2.1094. Min Act: -0.0001
Data Index: 89059 (C4 (Web Text))
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7063. Min Range: -2.7063
Max Act: 1.7730. Min Act: -0.0001
Data Index: 1187222 (C4 (Web Text))
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7063. Min Range: -2.7063
Max Act: 1.8381. Min Act: -0.0001
Data Index: 865776 (C4 (Web Text))
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7063. Min Range: -2.7063
Max Act: 2.0602. Min Act: -0.0001
Data Index: 131852 (C4 (Web Text))
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7063. Min Range: -2.7063
Max Act: 2.0479. Min Act: -0.0001
Data Index: 1002263 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7063. Min Range: -2.7063
Max Act: 1.9238. Min Act: -0.0001
Data Index: 740798 (C4 (Web Text))
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7063. Min Range: -2.7063
Max Act: 1.9711. Min Act: -0.0001
Data Index: 315484 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7063. Min Range: -2.7063
Max Act: 1.8376. Min Act: -0.0001
Data Index: 447021 (C4 (Web Text))
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19