Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2148 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.3964. Min Range: -1.3964
Max Act: 1.3964. Min Act: -0.0001
Data Index: 239797 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3964. Min Range: -1.3964
Max Act: 1.3029. Min Act: -0.0001
Data Index: 477081 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3964. Min Range: -1.3964
Max Act: 1.2355. Min Act: -0.0001
Data Index: 116108 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3964. Min Range: -1.3964
Max Act: 1.2455. Min Act: -0.0001
Data Index: 1032403 (C4 (Web Text))
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3964. Min Range: -1.3964
Max Act: 1.2013. Min Act: -0.0001
Data Index: 1005392 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3964. Min Range: -1.3964
Max Act: 1.2044. Min Act: -0.0001
Data Index: 506484 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3964. Min Range: -1.3964
Max Act: 1.1515. Min Act: -0.0001
Data Index: 1192665 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3964. Min Range: -1.3964
Max Act: 1.1255. Min Act: -0.0001
Data Index: 1349763 (C4 (Web Text))
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3964. Min Range: -1.3964
Max Act: 1.0506. Min Act: -0.0001
Data Index: 18942 (C4 (Web Text))
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3964. Min Range: -1.3964
Max Act: 1.1306. Min Act: -0.0001
Data Index: 1071434 (C4 (Web Text))
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3964. Min Range: -1.3964
Max Act: 1.0703. Min Act: -0.0001
Data Index: 1229933 (C4 (Web Text))
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3964. Min Range: -1.3964
Max Act: 1.0870. Min Act: -0.0001
Data Index: 1069176 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3964. Min Range: -1.3964
Max Act: 1.0907. Min Act: -0.0001
Data Index: 923896 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3964. Min Range: -1.3964
Max Act: 1.0011. Min Act: -0.0001
Data Index: 1331858 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3964. Min Range: -1.3964
Max Act: 1.0086. Min Act: -0.0001
Data Index: 948281 (C4 (Web Text))
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3964. Min Range: -1.3964
Max Act: 1.0745. Min Act: -0.0001
Data Index: 179246 (C4 (Web Text))
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3964. Min Range: -1.3964
Max Act: 1.0680. Min Act: -0.0001
Data Index: 1162829 (C4 (Web Text))
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3964. Min Range: -1.3964
Max Act: 1.0582. Min Act: -0.0001
Data Index: 358718 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3964. Min Range: -1.3964
Max Act: 1.0513. Min Act: -0.0001
Data Index: 1280557 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3964. Min Range: -1.3964
Max Act: 0.9863. Min Act: -0.0001
Data Index: 930772 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19