Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1797 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.0679. Min Range: -2.0679
Max Act: 1.9876. Min Act: -0.0001
Data Index: 847497 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0679. Min Range: -2.0679
Max Act: 2.0679. Min Act: -0.0001
Data Index: 140492 (C4 (Web Text))
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0679. Min Range: -2.0679
Max Act: 1.8313. Min Act: -0.0001
Data Index: 945433 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0679. Min Range: -2.0679
Max Act: 1.8766. Min Act: -0.0001
Data Index: 22964 (C4 (Web Text))
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0679. Min Range: -2.0679
Max Act: 1.9192. Min Act: -0.0001
Data Index: 1011035 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0679. Min Range: -2.0679
Max Act: 1.8644. Min Act: -0.0001
Data Index: 173963 (C4 (Web Text))
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0679. Min Range: -2.0679
Max Act: 1.8312. Min Act: -0.0001
Data Index: 1158034 (C4 (Web Text))
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0679. Min Range: -2.0679
Max Act: 2.0002. Min Act: -0.0001
Data Index: 772477 (C4 (Web Text))
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0679. Min Range: -2.0679
Max Act: 1.9954. Min Act: -0.0001
Data Index: 594799 (C4 (Web Text))
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0679. Min Range: -2.0679
Max Act: 1.8318. Min Act: -0.0001
Data Index: 124522 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0679. Min Range: -2.0679
Max Act: 1.7847. Min Act: -0.0001
Data Index: 1238436 (C4 (Web Text))
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0679. Min Range: -2.0679
Max Act: 1.7600. Min Act: -0.0001
Data Index: 569305 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0679. Min Range: -2.0679
Max Act: 1.7893. Min Act: -0.0001
Data Index: 1106722 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0679. Min Range: -2.0679
Max Act: 1.7618. Min Act: -0.0001
Data Index: 402707 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0679. Min Range: -2.0679
Max Act: 1.7533. Min Act: -0.0001
Data Index: 502103 (C4 (Web Text))
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0679. Min Range: -2.0679
Max Act: 1.7400. Min Act: -0.0001
Data Index: 891248 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0679. Min Range: -2.0679
Max Act: 1.7330. Min Act: -0.0001
Data Index: 60675 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0679. Min Range: -2.0679
Max Act: 1.7644. Min Act: -0.0001
Data Index: 1238154 (C4 (Web Text))
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0679. Min Range: -2.0679
Max Act: 1.7164. Min Act: -0.0001
Data Index: 655711 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0679. Min Range: -2.0679
Max Act: 1.7042. Min Act: -0.0001
Data Index: 1162051 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #19