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

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

Neuron 5457 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3686. Min Range: -1.3686

Max Act: 1.3686. Min Act: -0.0000

Data Index: 1428864 (Python Code)

Max Activating Token Index: 814

Text #1

Max Range: 1.3686. Min Range: -1.3686

Max Act: 1.1088. Min Act: -0.0000

Data Index: 1147397 (C4 (Web Text))

Max Activating Token Index: 218

Text #2

Max Range: 1.3686. Min Range: -1.3686

Max Act: 1.2159. Min Act: -0.0000

Data Index: 585930 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 1.3686. Min Range: -1.3686

Max Act: 1.1621. Min Act: -0.0000

Data Index: 101569 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 1.3686. Min Range: -1.3686

Max Act: 1.1006. Min Act: -0.0000

Data Index: 863603 (C4 (Web Text))

Max Activating Token Index: 181

Text #5

Max Range: 1.3686. Min Range: -1.3686

Max Act: 1.1122. Min Act: -0.0000

Data Index: 148884 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 1.3686. Min Range: -1.3686

Max Act: 1.0342. Min Act: -0.0000

Data Index: 448238 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 1.3686. Min Range: -1.3686

Max Act: 0.9957. Min Act: -0.0000

Data Index: 1199921 (C4 (Web Text))

Max Activating Token Index: 264

Text #8

Max Range: 1.3686. Min Range: -1.3686

Max Act: 1.0165. Min Act: -0.0000

Data Index: 483622 (C4 (Web Text))

Max Activating Token Index: 429

Text #9

Max Range: 1.3686. Min Range: -1.3686

Max Act: 1.0320. Min Act: -0.0000

Data Index: 586652 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 1.3686. Min Range: -1.3686

Max Act: 1.0060. Min Act: -0.0000

Data Index: 607942 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 1.3686. Min Range: -1.3686

Max Act: 0.9853. Min Act: -0.0000

Data Index: 1010150 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 1.3686. Min Range: -1.3686

Max Act: 0.9801. Min Act: -0.0000

Data Index: 318772 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 1.3686. Min Range: -1.3686

Max Act: 0.9929. Min Act: -0.0000

Data Index: 1237876 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 1.3686. Min Range: -1.3686

Max Act: 0.9222. Min Act: -0.0000

Data Index: 1599662 (Python Code)

Max Activating Token Index: 63

Text #15

Max Range: 1.3686. Min Range: -1.3686

Max Act: 0.9377. Min Act: -0.0000

Data Index: 1412535 (Python Code)

Max Activating Token Index: 18

Text #16

Max Range: 1.3686. Min Range: -1.3686

Max Act: 0.9238. Min Act: -0.0000

Data Index: 2676 (C4 (Web Text))

Max Activating Token Index: 722

Text #17

Max Range: 1.3686. Min Range: -1.3686

Max Act: 0.9228. Min Act: -0.0000

Data Index: 1294256 (C4 (Web Text))

Max Activating Token Index: 99

Text #18

Max Range: 1.3686. Min Range: -1.3686

Max Act: 0.9509. Min Act: -0.0000

Data Index: 1641186 (Python Code)

Max Activating Token Index: 916

Text #19

Max Range: 1.3686. Min Range: -1.3686

Max Act: 0.8941. Min Act: -0.0000

Data Index: 564694 (C4 (Web Text))

Max Activating Token Index: 176