Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4464 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.2360. Min Range: -2.2360
Max Act: 2.1359. Min Act: -0.0001
Data Index: 317269 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2360. Min Range: -2.2360
Max Act: 2.2360. Min Act: -0.0001
Data Index: 1147542 (C4 (Web Text))
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2360. Min Range: -2.2360
Max Act: 2.1292. Min Act: -0.0000
Data Index: 971017 (C4 (Web Text))
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2360. Min Range: -2.2360
Max Act: 1.9729. Min Act: -0.0001
Data Index: 216866 (C4 (Web Text))
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2360. Min Range: -2.2360
Max Act: 1.8988. Min Act: -0.0000
Data Index: 1155917 (C4 (Web Text))
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2360. Min Range: -2.2360
Max Act: 1.9846. Min Act: -0.0001
Data Index: 156222 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2360. Min Range: -2.2360
Max Act: 1.8613. Min Act: -0.0001
Data Index: 1096182 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2360. Min Range: -2.2360
Max Act: 1.7354. Min Act: -0.0001
Data Index: 668292 (C4 (Web Text))
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2360. Min Range: -2.2360
Max Act: 1.9196. Min Act: -0.0001
Data Index: 427373 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2360. Min Range: -2.2360
Max Act: 1.8036. Min Act: -0.0001
Data Index: 185357 (C4 (Web Text))
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2360. Min Range: -2.2360
Max Act: 1.7923. Min Act: -0.0001
Data Index: 845176 (C4 (Web Text))
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2360. Min Range: -2.2360
Max Act: 1.7912. Min Act: -0.0000
Data Index: 1155319 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2360. Min Range: -2.2360
Max Act: 1.7699. Min Act: -0.0001
Data Index: 393121 (C4 (Web Text))
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2360. Min Range: -2.2360
Max Act: 1.7589. Min Act: -0.0001
Data Index: 986762 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2360. Min Range: -2.2360
Max Act: 1.7447. Min Act: -0.0001
Data Index: 1250622 (C4 (Web Text))
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2360. Min Range: -2.2360
Max Act: 1.6312. Min Act: -0.0001
Data Index: 490456 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2360. Min Range: -2.2360
Max Act: 1.7037. Min Act: -0.0001
Data Index: 351702 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2360. Min Range: -2.2360
Max Act: 1.7715. Min Act: -0.0001
Data Index: 609739 (C4 (Web Text))
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2360. Min Range: -2.2360
Max Act: 1.6938. Min Act: -0.0001
Data Index: 22565 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2360. Min Range: -2.2360
Max Act: 1.7877. Min Act: -0.0001
Data Index: 10544 (C4 (Web Text))
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #19