Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3163 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 3.6151. Min Range: -3.6151
Max Act: 3.6151. Min Act: -0.0001
Data Index: 925165 (C4 (Web Text))
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6151. Min Range: -3.6151
Max Act: 3.4000. Min Act: -0.0001
Data Index: 6283 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6151. Min Range: -3.6151
Max Act: 3.2633. Min Act: -0.0001
Data Index: 78769 (C4 (Web Text))
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6151. Min Range: -3.6151
Max Act: 2.9931. Min Act: -0.0001
Data Index: 295623 (C4 (Web Text))
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6151. Min Range: -3.6151
Max Act: 2.9110. Min Act: -0.0001
Data Index: 1078083 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6151. Min Range: -3.6151
Max Act: 3.0222. Min Act: -0.0001
Data Index: 746806 (C4 (Web Text))
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6151. Min Range: -3.6151
Max Act: 2.8449. Min Act: -0.0001
Data Index: 13293 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6151. Min Range: -3.6151
Max Act: 2.5374. Min Act: -0.0001
Data Index: 1238230 (C4 (Web Text))
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6151. Min Range: -3.6151
Max Act: 2.4686. Min Act: -0.0001
Data Index: 119343 (C4 (Web Text))
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6151. Min Range: -3.6151
Max Act: 2.8209. Min Act: -0.0001
Data Index: 1014358 (C4 (Web Text))
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6151. Min Range: -3.6151
Max Act: 2.5321. Min Act: -0.0001
Data Index: 229417 (C4 (Web Text))
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6151. Min Range: -3.6151
Max Act: 2.6743. Min Act: -0.0001
Data Index: 969904 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6151. Min Range: -3.6151
Max Act: 2.6188. Min Act: -0.0001
Data Index: 866737 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6151. Min Range: -3.6151
Max Act: 2.5350. Min Act: -0.0001
Data Index: 1280986 (C4 (Web Text))
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6151. Min Range: -3.6151
Max Act: 2.5424. Min Act: -0.0001
Data Index: 307541 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6151. Min Range: -3.6151
Max Act: 2.3725. Min Act: -0.0001
Data Index: 267012 (C4 (Web Text))
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6151. Min Range: -3.6151
Max Act: 2.1654. Min Act: -0.0001
Data Index: 297419 (C4 (Web Text))
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6151. Min Range: -3.6151
Max Act: 2.6021. Min Act: -0.0001
Data Index: 884836 (C4 (Web Text))
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6151. Min Range: -3.6151
Max Act: 2.4563. Min Act: -0.0001
Data Index: 89767 (C4 (Web Text))
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6151. Min Range: -3.6151
Max Act: 2.3124. Min Act: -0.0001
Data Index: 1030718 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #19