Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2526 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.3744. Min Range: -1.3744
Max Act: 1.3744. Min Act: -0.0001
Data Index: 739843 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3744. Min Range: -1.3744
Max Act: 1.3295. Min Act: -0.0001
Data Index: 729609 (C4 (Web Text))
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3744. Min Range: -1.3744
Max Act: 1.3252. Min Act: -0.0001
Data Index: 764180 (C4 (Web Text))
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3744. Min Range: -1.3744
Max Act: 1.2581. Min Act: -0.0001
Data Index: 891177 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3744. Min Range: -1.3744
Max Act: 1.0110. Min Act: -0.0001
Data Index: 1077884 (C4 (Web Text))
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3744. Min Range: -1.3744
Max Act: 0.9916. Min Act: -0.0001
Data Index: 1105747 (C4 (Web Text))
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3744. Min Range: -1.3744
Max Act: 0.9026. Min Act: -0.0001
Data Index: 866931 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3744. Min Range: -1.3744
Max Act: 0.9273. Min Act: -0.0001
Data Index: 61823 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3744. Min Range: -1.3744
Max Act: 0.8694. Min Act: -0.0001
Data Index: 1247020 (C4 (Web Text))
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3744. Min Range: -1.3744
Max Act: 0.8878. Min Act: -0.0001
Data Index: 258081 (C4 (Web Text))
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3744. Min Range: -1.3744
Max Act: 0.8887. Min Act: -0.0001
Data Index: 925553 (C4 (Web Text))
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3744. Min Range: -1.3744
Max Act: 0.8667. Min Act: -0.0001
Data Index: 172312 (C4 (Web Text))
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3744. Min Range: -1.3744
Max Act: 0.8612. Min Act: -0.0001
Data Index: 846013 (C4 (Web Text))
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3744. Min Range: -1.3744
Max Act: 0.8268. Min Act: -0.0001
Data Index: 229542 (C4 (Web Text))
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3744. Min Range: -1.3744
Max Act: 0.9073. Min Act: -0.0001
Data Index: 251254 (C4 (Web Text))
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3744. Min Range: -1.3744
Max Act: 0.8011. Min Act: -0.0001
Data Index: 561685 (C4 (Web Text))
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3744. Min Range: -1.3744
Max Act: 0.7691. Min Act: -0.0001
Data Index: 1295011 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3744. Min Range: -1.3744
Max Act: 0.7679. Min Act: -0.0001
Data Index: 849929 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3744. Min Range: -1.3744
Max Act: 0.7611. Min Act: -0.0001
Data Index: 156532 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3744. Min Range: -1.3744
Max Act: 0.7555. Min Act: -0.0001
Data Index: 60928 (C4 (Web Text))
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #19