Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1745 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 2.2566. Min Range: -2.2566
Max Act: 2.2566. Min Act: -0.0001
Data Index: 26888 (C4 (Web Text))
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2566. Min Range: -2.2566
Max Act: 2.2267. Min Act: -0.0001
Data Index: 1291934 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2566. Min Range: -2.2566
Max Act: 2.0584. Min Act: -0.0001
Data Index: 505797 (C4 (Web Text))
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2566. Min Range: -2.2566
Max Act: 2.1563. Min Act: -0.0001
Data Index: 283308 (C4 (Web Text))
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2566. Min Range: -2.2566
Max Act: 2.0312. Min Act: -0.0001
Data Index: 1047872 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2566. Min Range: -2.2566
Max Act: 2.0139. Min Act: -0.0001
Data Index: 56636 (C4 (Web Text))
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2566. Min Range: -2.2566
Max Act: 1.9221. Min Act: -0.0001
Data Index: 1187101 (C4 (Web Text))
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2566. Min Range: -2.2566
Max Act: 1.9073. Min Act: -0.0001
Data Index: 963097 (C4 (Web Text))
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2566. Min Range: -2.2566
Max Act: 1.7169. Min Act: -0.0001
Data Index: 183870 (C4 (Web Text))
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2566. Min Range: -2.2566
Max Act: 1.8605. Min Act: -0.0001
Data Index: 229979 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2566. Min Range: -2.2566
Max Act: 1.9068. Min Act: -0.0001
Data Index: 844289 (C4 (Web Text))
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2566. Min Range: -2.2566
Max Act: 1.9738. Min Act: -0.0001
Data Index: 816704 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2566. Min Range: -2.2566
Max Act: 1.8205. Min Act: -0.0001
Data Index: 509387 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2566. Min Range: -2.2566
Max Act: 1.7402. Min Act: -0.0001
Data Index: 230692 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2566. Min Range: -2.2566
Max Act: 1.7712. Min Act: -0.0001
Data Index: 933275 (C4 (Web Text))
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2566. Min Range: -2.2566
Max Act: 1.7187. Min Act: -0.0001
Data Index: 112618 (C4 (Web Text))
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2566. Min Range: -2.2566
Max Act: 1.7545. Min Act: -0.0001
Data Index: 307792 (C4 (Web Text))
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2566. Min Range: -2.2566
Max Act: 1.7937. Min Act: -0.0001
Data Index: 532138 (C4 (Web Text))
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2566. Min Range: -2.2566
Max Act: 1.6432. Min Act: -0.0001
Data Index: 1076643 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2566. Min Range: -2.2566
Max Act: 1.7247. Min Act: -0.0001
Data Index: 395755 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19