Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4068 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.9264. Min Range: -2.9264
Max Act: 2.8875. Min Act: -0.0001
Data Index: 1003926 (C4 (Web Text))
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9264. Min Range: -2.9264
Max Act: 2.9264. Min Act: -0.0001
Data Index: 612238 (C4 (Web Text))
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9264. Min Range: -2.9264
Max Act: 2.7309. Min Act: -0.0001
Data Index: 1430188 (Python Code)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9264. Min Range: -2.9264
Max Act: 2.6451. Min Act: -0.0001
Data Index: 47655 (C4 (Web Text))
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9264. Min Range: -2.9264
Max Act: 2.5955. Min Act: -0.0001
Data Index: 988869 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9264. Min Range: -2.9264
Max Act: 2.5565. Min Act: -0.0001
Data Index: 798055 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9264. Min Range: -2.9264
Max Act: 2.6780. Min Act: -0.0001
Data Index: 219695 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9264. Min Range: -2.9264
Max Act: 2.4059. Min Act: -0.0001
Data Index: 1265161 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9264. Min Range: -2.9264
Max Act: 2.5074. Min Act: -0.0001
Data Index: 1079926 (C4 (Web Text))
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9264. Min Range: -2.9264
Max Act: 2.4932. Min Act: -0.0001
Data Index: 9254 (C4 (Web Text))
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9264. Min Range: -2.9264
Max Act: 2.4979. Min Act: -0.0001
Data Index: 1041003 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9264. Min Range: -2.9264
Max Act: 2.5981. Min Act: -0.0001
Data Index: 1032214 (C4 (Web Text))
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9264. Min Range: -2.9264
Max Act: 2.4834. Min Act: -0.0001
Data Index: 1178929 (C4 (Web Text))
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9264. Min Range: -2.9264
Max Act: 2.4715. Min Act: -0.0001
Data Index: 612372 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9264. Min Range: -2.9264
Max Act: 2.2996. Min Act: -0.0001
Data Index: 619292 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9264. Min Range: -2.9264
Max Act: 2.3056. Min Act: -0.0001
Data Index: 41556 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9264. Min Range: -2.9264
Max Act: 2.4162. Min Act: -0.0001
Data Index: 1539036 (Python Code)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9264. Min Range: -2.9264
Max Act: 2.5012. Min Act: -0.0001
Data Index: 1242912 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9264. Min Range: -2.9264
Max Act: 2.3788. Min Act: -0.0001
Data Index: 463619 (C4 (Web Text))
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9264. Min Range: -2.9264
Max Act: 2.4977. Min Act: -0.0001
Data Index: 547032 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #19