Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3672 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.2026. Min Range: -1.2026
Max Act: 1.0874. Min Act: -0.0001
Data Index: 155264 (C4 (Web Text))
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2026. Min Range: -1.2026
Max Act: 1.1218. Min Act: -0.0001
Data Index: 1228186 (C4 (Web Text))
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2026. Min Range: -1.2026
Max Act: 1.1744. Min Act: -0.0001
Data Index: 1285983 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2026. Min Range: -1.2026
Max Act: 1.1521. Min Act: -0.0001
Data Index: 156472 (C4 (Web Text))
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2026. Min Range: -1.2026
Max Act: 1.2026. Min Act: -0.0001
Data Index: 375875 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2026. Min Range: -1.2026
Max Act: 1.1682. Min Act: -0.0001
Data Index: 809316 (C4 (Web Text))
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2026. Min Range: -1.2026
Max Act: 1.1362. Min Act: -0.0001
Data Index: 871363 (C4 (Web Text))
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2026. Min Range: -1.2026
Max Act: 1.0695. Min Act: -0.0001
Data Index: 23756 (C4 (Web Text))
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2026. Min Range: -1.2026
Max Act: 1.1662. Min Act: -0.0001
Data Index: 221221 (C4 (Web Text))
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2026. Min Range: -1.2026
Max Act: 1.1190. Min Act: -0.0001
Data Index: 283014 (C4 (Web Text))
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2026. Min Range: -1.2026
Max Act: 1.0499. Min Act: -0.0001
Data Index: 617211 (C4 (Web Text))
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2026. Min Range: -1.2026
Max Act: 1.0642. Min Act: -0.0001
Data Index: 576836 (C4 (Web Text))
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2026. Min Range: -1.2026
Max Act: 1.0968. Min Act: -0.0001
Data Index: 329443 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2026. Min Range: -1.2026
Max Act: 1.0160. Min Act: -0.0001
Data Index: 635516 (C4 (Web Text))
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2026. Min Range: -1.2026
Max Act: 0.9862. Min Act: -0.0001
Data Index: 116930 (C4 (Web Text))
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2026. Min Range: -1.2026
Max Act: 1.1118. Min Act: -0.0001
Data Index: 851556 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2026. Min Range: -1.2026
Max Act: 1.0122. Min Act: -0.0001
Data Index: 1114006 (C4 (Web Text))
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2026. Min Range: -1.2026
Max Act: 1.0393. Min Act: -0.0001
Data Index: 1035499 (C4 (Web Text))
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2026. Min Range: -1.2026
Max Act: 1.0325. Min Act: -0.0001
Data Index: 499661 (C4 (Web Text))
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2026. Min Range: -1.2026
Max Act: 1.0335. Min Act: -0.0001
Data Index: 1212278 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19