Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1888 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 4.3609. Min Range: -4.3609
Max Act: 4.3609. Min Act: -0.0001
Data Index: 1349969 (C4 (Web Text))
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3609. Min Range: -4.3609
Max Act: 4.2907. Min Act: -0.0001
Data Index: 28813 (C4 (Web Text))
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3609. Min Range: -4.3609
Max Act: 4.3537. Min Act: -0.0001
Data Index: 575165 (C4 (Web Text))
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3609. Min Range: -4.3609
Max Act: 3.9554. Min Act: -0.0001
Data Index: 488127 (C4 (Web Text))
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3609. Min Range: -4.3609
Max Act: 3.7152. Min Act: -0.0001
Data Index: 869181 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3609. Min Range: -4.3609
Max Act: 3.7867. Min Act: -0.0001
Data Index: 224705 (C4 (Web Text))
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3609. Min Range: -4.3609
Max Act: 3.9010. Min Act: -0.0001
Data Index: 602822 (C4 (Web Text))
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3609. Min Range: -4.3609
Max Act: 3.6679. Min Act: -0.0001
Data Index: 230142 (C4 (Web Text))
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3609. Min Range: -4.3609
Max Act: 3.6411. Min Act: -0.0001
Data Index: 1290605 (C4 (Web Text))
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3609. Min Range: -4.3609
Max Act: 3.5137. Min Act: -0.0001
Data Index: 1249794 (C4 (Web Text))
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3609. Min Range: -4.3609
Max Act: 3.6421. Min Act: -0.0001
Data Index: 1277687 (C4 (Web Text))
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3609. Min Range: -4.3609
Max Act: 3.4381. Min Act: -0.0001
Data Index: 189690 (C4 (Web Text))
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3609. Min Range: -4.3609
Max Act: 3.4013. Min Act: -0.0001
Data Index: 190155 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3609. Min Range: -4.3609
Max Act: 3.3998. Min Act: -0.0001
Data Index: 188127 (C4 (Web Text))
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3609. Min Range: -4.3609
Max Act: 3.4707. Min Act: -0.0001
Data Index: 1102007 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3609. Min Range: -4.3609
Max Act: 3.3063. Min Act: -0.0001
Data Index: 1022444 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3609. Min Range: -4.3609
Max Act: 3.1417. Min Act: -0.0001
Data Index: 377786 (C4 (Web Text))
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3609. Min Range: -4.3609
Max Act: 3.2894. Min Act: -0.0001
Data Index: 44385 (C4 (Web Text))
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3609. Min Range: -4.3609
Max Act: 3.2573. Min Act: -0.0001
Data Index: 925781 (C4 (Web Text))
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3609. Min Range: -4.3609
Max Act: 2.9178. Min Act: -0.0001
Data Index: 1144061 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19