Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5847 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3825. Min Range: -0.3825

Max Act: 0.3825. Min Act: -0.0000

Data Index: 1206116 (C4 (Web Text))

Max Activating Token Index: 611

Text #1

Max Range: 0.3825. Min Range: -0.3825

Max Act: 0.3390. Min Act: -0.0000

Data Index: 1291312 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 0.3825. Min Range: -0.3825

Max Act: 0.3287. Min Act: -0.0000

Data Index: 512911 (C4 (Web Text))

Max Activating Token Index: 498

Text #3

Max Range: 0.3825. Min Range: -0.3825

Max Act: 0.3398. Min Act: -0.0000

Data Index: 575365 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 0.3825. Min Range: -0.3825

Max Act: 0.3361. Min Act: -0.0000

Data Index: 1216599 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 0.3825. Min Range: -0.3825

Max Act: 0.3241. Min Act: -0.0000

Data Index: 1269183 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 0.3825. Min Range: -0.3825

Max Act: 0.3319. Min Act: -0.0000

Data Index: 1240908 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 0.3825. Min Range: -0.3825

Max Act: 0.3512. Min Act: -0.0000

Data Index: 66060 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 0.3825. Min Range: -0.3825

Max Act: 0.3281. Min Act: -0.0000

Data Index: 85078 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 0.3825. Min Range: -0.3825

Max Act: 0.3301. Min Act: -0.0000

Data Index: 197162 (C4 (Web Text))

Max Activating Token Index: 839

Text #10

Max Range: 0.3825. Min Range: -0.3825

Max Act: 0.3296. Min Act: -0.0000

Data Index: 763074 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 0.3825. Min Range: -0.3825

Max Act: 0.3159. Min Act: -0.0000

Data Index: 1073783 (C4 (Web Text))

Max Activating Token Index: 182

Text #12

Max Range: 0.3825. Min Range: -0.3825

Max Act: 0.3246. Min Act: -0.0000

Data Index: 382033 (C4 (Web Text))

Max Activating Token Index: 872

Text #13

Max Range: 0.3825. Min Range: -0.3825

Max Act: 0.3060. Min Act: -0.0000

Data Index: 1113664 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 0.3825. Min Range: -0.3825

Max Act: 0.2781. Min Act: -0.0000

Data Index: 1115023 (C4 (Web Text))

Max Activating Token Index: 949

Text #15

Max Range: 0.3825. Min Range: -0.3825

Max Act: 0.2996. Min Act: -0.0000

Data Index: 1088697 (C4 (Web Text))

Max Activating Token Index: 270

Text #16

Max Range: 0.3825. Min Range: -0.3825

Max Act: 0.2832. Min Act: -0.0000

Data Index: 1057784 (C4 (Web Text))

Max Activating Token Index: 16

Text #17

Max Range: 0.3825. Min Range: -0.3825

Max Act: 0.2916. Min Act: -0.0000

Data Index: 474117 (C4 (Web Text))

Max Activating Token Index: 332

Text #18

Max Range: 0.3825. Min Range: -0.3825

Max Act: 0.2924. Min Act: -0.0000

Data Index: 1177452 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 0.3825. Min Range: -0.3825

Max Act: 0.2906. Min Act: -0.0000

Data Index: 660673 (C4 (Web Text))

Max Activating Token Index: 716