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

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

Neuron 1058 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.8171. Min Range: -1.8171

Max Act: 1.8171. Min Act: -0.0002

Data Index: 309980 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 1.8171. Min Range: -1.8171

Max Act: 1.6361. Min Act: -0.0002

Data Index: 454212 (C4 (Web Text))

Max Activating Token Index: 285

Text #2

Max Range: 1.8171. Min Range: -1.8171

Max Act: 1.5247. Min Act: -0.0002

Data Index: 795694 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 1.8171. Min Range: -1.8171

Max Act: 1.5792. Min Act: -0.0002

Data Index: 281502 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 1.8171. Min Range: -1.8171

Max Act: 1.5245. Min Act: -0.0002

Data Index: 1200945 (C4 (Web Text))

Max Activating Token Index: 120

Text #5

Max Range: 1.8171. Min Range: -1.8171

Max Act: 1.5317. Min Act: -0.0002

Data Index: 1013270 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 1.8171. Min Range: -1.8171

Max Act: 1.5663. Min Act: -0.0002

Data Index: 1048047 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 1.8171. Min Range: -1.8171

Max Act: 1.4833. Min Act: -0.0002

Data Index: 214119 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 1.8171. Min Range: -1.8171

Max Act: 1.4889. Min Act: -0.0002

Data Index: 1287397 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 1.8171. Min Range: -1.8171

Max Act: 1.5304. Min Act: -0.0002

Data Index: 798264 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 1.8171. Min Range: -1.8171

Max Act: 1.5080. Min Act: -0.0002

Data Index: 367808 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 1.8171. Min Range: -1.8171

Max Act: 1.4713. Min Act: -0.0002

Data Index: 504899 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 1.8171. Min Range: -1.8171

Max Act: 1.5202. Min Act: -0.0002

Data Index: 7576 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 1.8171. Min Range: -1.8171

Max Act: 1.4725. Min Act: -0.0002

Data Index: 248874 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 1.8171. Min Range: -1.8171

Max Act: 1.4960. Min Act: -0.0002

Data Index: 354679 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 1.8171. Min Range: -1.8171

Max Act: 1.4340. Min Act: -0.0002

Data Index: 1062565 (C4 (Web Text))

Max Activating Token Index: 107

Text #16

Max Range: 1.8171. Min Range: -1.8171

Max Act: 1.4325. Min Act: -0.0002

Data Index: 395987 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 1.8171. Min Range: -1.8171

Max Act: 1.4297. Min Act: -0.0002

Data Index: 983712 (C4 (Web Text))

Max Activating Token Index: 860

Text #18

Max Range: 1.8171. Min Range: -1.8171

Max Act: 1.4702. Min Act: -0.0002

Data Index: 1296709 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 1.8171. Min Range: -1.8171

Max Act: 1.4237. Min Act: -0.0002

Data Index: 1182816 (C4 (Web Text))

Max Activating Token Index: 50