Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 17 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.6726. Min Range: -2.6726
Max Act: 2.6726. Min Act: -0.0001
Data Index: 1102937 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6726. Min Range: -2.6726
Max Act: 2.5085. Min Act: -0.0001
Data Index: 1224211 (C4 (Web Text))
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6726. Min Range: -2.6726
Max Act: 2.5926. Min Act: -0.0001
Data Index: 48442 (C4 (Web Text))
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6726. Min Range: -2.6726
Max Act: 2.3584. Min Act: -0.0001
Data Index: 1138638 (C4 (Web Text))
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6726. Min Range: -2.6726
Max Act: 2.4448. Min Act: -0.0001
Data Index: 1473964 (Python Code)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6726. Min Range: -2.6726
Max Act: 2.0941. Min Act: -0.0001
Data Index: 88840 (C4 (Web Text))
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6726. Min Range: -2.6726
Max Act: 2.1337. Min Act: -0.0001
Data Index: 394954 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6726. Min Range: -2.6726
Max Act: 2.1989. Min Act: -0.0001
Data Index: 1004375 (C4 (Web Text))
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6726. Min Range: -2.6726
Max Act: 2.0374. Min Act: -0.0001
Data Index: 1416778 (Python Code)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6726. Min Range: -2.6726
Max Act: 2.1433. Min Act: -0.0001
Data Index: 1415144 (Python Code)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6726. Min Range: -2.6726
Max Act: 2.3513. Min Act: -0.0001
Data Index: 197157 (C4 (Web Text))
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6726. Min Range: -2.6726
Max Act: 1.9975. Min Act: -0.0001
Data Index: 587841 (C4 (Web Text))
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6726. Min Range: -2.6726
Max Act: 1.9336. Min Act: -0.0001
Data Index: 1305317 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6726. Min Range: -2.6726
Max Act: 1.9742. Min Act: -0.0001
Data Index: 392240 (C4 (Web Text))
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6726. Min Range: -2.6726
Max Act: 1.9393. Min Act: -0.0001
Data Index: 261582 (C4 (Web Text))
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6726. Min Range: -2.6726
Max Act: 1.9901. Min Act: -0.0001
Data Index: 1512406 (Python Code)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6726. Min Range: -2.6726
Max Act: 1.9277. Min Act: -0.0001
Data Index: 178976 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6726. Min Range: -2.6726
Max Act: 1.9719. Min Act: -0.0001
Data Index: 1202074 (C4 (Web Text))
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6726. Min Range: -2.6726
Max Act: 1.9195. Min Act: -0.0001
Data Index: 1400623 (Python Code)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6726. Min Range: -2.6726
Max Act: 1.8990. Min Act: -0.0001
Data Index: 605310 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #19