Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1803 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.1187. Min Range: -2.1187
Max Act: 2.1187. Min Act: -0.0001
Data Index: 62892 (C4 (Web Text))
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1187. Min Range: -2.1187
Max Act: 1.5098. Min Act: -0.0001
Data Index: 1157613 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1187. Min Range: -2.1187
Max Act: 1.5582. Min Act: -0.0001
Data Index: 300821 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1187. Min Range: -2.1187
Max Act: 1.4648. Min Act: -0.0001
Data Index: 16759 (C4 (Web Text))
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1187. Min Range: -2.1187
Max Act: 1.5013. Min Act: -0.0001
Data Index: 14032 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1187. Min Range: -2.1187
Max Act: 1.5505. Min Act: -0.0001
Data Index: 744023 (C4 (Web Text))
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1187. Min Range: -2.1187
Max Act: 1.4496. Min Act: -0.0001
Data Index: 302501 (C4 (Web Text))
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1187. Min Range: -2.1187
Max Act: 1.4143. Min Act: -0.0001
Data Index: 568057 (C4 (Web Text))
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1187. Min Range: -2.1187
Max Act: 1.3043. Min Act: -0.0001
Data Index: 24289 (C4 (Web Text))
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1187. Min Range: -2.1187
Max Act: 1.3791. Min Act: -0.0001
Data Index: 1283741 (C4 (Web Text))
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1187. Min Range: -2.1187
Max Act: 1.3505. Min Act: -0.0001
Data Index: 309962 (C4 (Web Text))
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1187. Min Range: -2.1187
Max Act: 1.2368. Min Act: -0.0001
Data Index: 443671 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1187. Min Range: -2.1187
Max Act: 1.1609. Min Act: -0.0001
Data Index: 915674 (C4 (Web Text))
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1187. Min Range: -2.1187
Max Act: 0.9632. Min Act: -0.0001
Data Index: 1295710 (C4 (Web Text))
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1187. Min Range: -2.1187
Max Act: 1.1581. Min Act: -0.0001
Data Index: 687283 (C4 (Web Text))
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1187. Min Range: -2.1187
Max Act: 1.1819. Min Act: -0.0001
Data Index: 709195 (C4 (Web Text))
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1187. Min Range: -2.1187
Max Act: 1.3488. Min Act: -0.0001
Data Index: 827549 (C4 (Web Text))
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1187. Min Range: -2.1187
Max Act: 1.3169. Min Act: -0.0001
Data Index: 801719 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1187. Min Range: -2.1187
Max Act: 1.1188. Min Act: -0.0001
Data Index: 700727 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1187. Min Range: -2.1187
Max Act: 1.1036. Min Act: -0.0001
Data Index: 231158 (C4 (Web Text))
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #19