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

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

Neuron 1823 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.8924. Min Act: -0.0000

Data Index: 1334036 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.7953. Min Act: -0.0000

Data Index: 569624 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.7829. Min Act: -0.0000

Data Index: 367196 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.7060. Min Act: -0.0000

Data Index: 574058 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.7206. Min Act: -0.0000

Data Index: 589478 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.6730. Min Act: -0.0000

Data Index: 365617 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.6412. Min Act: -0.0000

Data Index: 242263 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.6939. Min Act: -0.0000

Data Index: 226701 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.6797. Min Act: -0.0000

Data Index: 120936 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.5921. Min Act: -0.0000

Data Index: 697740 (C4 (Web Text))

Max Activating Token Index: 48

Text #10

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.6205. Min Act: -0.0000

Data Index: 1189847 (C4 (Web Text))

Max Activating Token Index: 343

Text #11

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.6433. Min Act: -0.0000

Data Index: 1136724 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.6465. Min Act: -0.0000

Data Index: 651693 (C4 (Web Text))

Max Activating Token Index: 323

Text #13

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.6117. Min Act: -0.0000

Data Index: 90773 (C4 (Web Text))

Max Activating Token Index: 206

Text #14

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.6258. Min Act: -0.0000

Data Index: 998925 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.6444. Min Act: -0.0000

Data Index: 928703 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.6228. Min Act: -0.0000

Data Index: 449385 (C4 (Web Text))

Max Activating Token Index: 136

Text #17

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.5069. Min Act: -0.0000

Data Index: 974520 (C4 (Web Text))

Max Activating Token Index: 350

Text #18

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.6314. Min Act: -0.0000

Data Index: 1070116 (C4 (Web Text))

Max Activating Token Index: 309

Text #19

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.5678. Min Act: -0.0000

Data Index: 275464 (C4 (Web Text))

Max Activating Token Index: 158