Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3472 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.3793. Min Range: -1.3793
Max Act: 1.3042. Min Act: -0.0001
Data Index: 11487 (C4 (Web Text))
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3793. Min Range: -1.3793
Max Act: 1.3744. Min Act: -0.0001
Data Index: 213829 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3793. Min Range: -1.3793
Max Act: 1.2852. Min Act: -0.0001
Data Index: 760355 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3793. Min Range: -1.3793
Max Act: 1.2629. Min Act: -0.0001
Data Index: 544654 (C4 (Web Text))
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3793. Min Range: -1.3793
Max Act: 1.1705. Min Act: -0.0001
Data Index: 1327502 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3793. Min Range: -1.3793
Max Act: 1.0436. Min Act: -0.0001
Data Index: 375761 (C4 (Web Text))
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3793. Min Range: -1.3793
Max Act: 1.1571. Min Act: -0.0001
Data Index: 962344 (C4 (Web Text))
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3793. Min Range: -1.3793
Max Act: 1.3793. Min Act: -0.0001
Data Index: 1569340 (Python Code)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3793. Min Range: -1.3793
Max Act: 1.1616. Min Act: -0.0001
Data Index: 623563 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3793. Min Range: -1.3793
Max Act: 1.1375. Min Act: -0.0001
Data Index: 197932 (C4 (Web Text))
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3793. Min Range: -1.3793
Max Act: 1.1703. Min Act: -0.0001
Data Index: 1457461 (Python Code)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3793. Min Range: -1.3793
Max Act: 1.1952. Min Act: -0.0001
Data Index: 1336464 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3793. Min Range: -1.3793
Max Act: 1.1579. Min Act: -0.0001
Data Index: 853606 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3793. Min Range: -1.3793
Max Act: 1.2862. Min Act: -0.0001
Data Index: 213442 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3793. Min Range: -1.3793
Max Act: 1.0637. Min Act: -0.0001
Data Index: 832239 (C4 (Web Text))
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3793. Min Range: -1.3793
Max Act: 1.0861. Min Act: -0.0001
Data Index: 963017 (C4 (Web Text))
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3793. Min Range: -1.3793
Max Act: 1.0414. Min Act: -0.0001
Data Index: 683633 (C4 (Web Text))
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3793. Min Range: -1.3793
Max Act: 1.1235. Min Act: -0.0001
Data Index: 336017 (C4 (Web Text))
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3793. Min Range: -1.3793
Max Act: 1.0399. Min Act: -0.0001
Data Index: 204885 (C4 (Web Text))
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3793. Min Range: -1.3793
Max Act: 1.0879. Min Act: -0.0001
Data Index: 1260791 (C4 (Web Text))
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #19