Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 27 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 3.9783. Min Range: -3.9783
Max Act: 3.9783. Min Act: -0.0001
Data Index: 1214319 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9783. Min Range: -3.9783
Max Act: 3.4521. Min Act: -0.0001
Data Index: 1262916 (C4 (Web Text))
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9783. Min Range: -3.9783
Max Act: 2.6764. Min Act: -0.0001
Data Index: 1232068 (C4 (Web Text))
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9783. Min Range: -3.9783
Max Act: 2.6222. Min Act: -0.0001
Data Index: 116142 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9783. Min Range: -3.9783
Max Act: 2.4741. Min Act: -0.0001
Data Index: 226902 (C4 (Web Text))
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9783. Min Range: -3.9783
Max Act: 2.2453. Min Act: -0.0001
Data Index: 296404 (C4 (Web Text))
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9783. Min Range: -3.9783
Max Act: 2.2640. Min Act: -0.0001
Data Index: 654460 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9783. Min Range: -3.9783
Max Act: 2.0355. Min Act: -0.0001
Data Index: 1130317 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9783. Min Range: -3.9783
Max Act: 2.2722. Min Act: -0.0001
Data Index: 1312743 (C4 (Web Text))
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9783. Min Range: -3.9783
Max Act: 2.1638. Min Act: -0.0001
Data Index: 231194 (C4 (Web Text))
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9783. Min Range: -3.9783
Max Act: 2.0163. Min Act: -0.0001
Data Index: 19163 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9783. Min Range: -3.9783
Max Act: 2.0092. Min Act: -0.0001
Data Index: 470113 (C4 (Web Text))
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9783. Min Range: -3.9783
Max Act: 2.0021. Min Act: -0.0001
Data Index: 456142 (C4 (Web Text))
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9783. Min Range: -3.9783
Max Act: 1.8865. Min Act: -0.0001
Data Index: 750660 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9783. Min Range: -3.9783
Max Act: 1.8252. Min Act: -0.0001
Data Index: 1212904 (C4 (Web Text))
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9783. Min Range: -3.9783
Max Act: 1.8180. Min Act: -0.0001
Data Index: 616254 (C4 (Web Text))
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9783. Min Range: -3.9783
Max Act: 1.7510. Min Act: -0.0001
Data Index: 1101287 (C4 (Web Text))
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9783. Min Range: -3.9783
Max Act: 1.8580. Min Act: -0.0001
Data Index: 402550 (C4 (Web Text))
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9783. Min Range: -3.9783
Max Act: 1.7951. Min Act: -0.0001
Data Index: 533532 (C4 (Web Text))
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9783. Min Range: -3.9783
Max Act: 1.7890. Min Act: -0.0001
Data Index: 1294340 (C4 (Web Text))
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19