Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2818 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.1173. Min Act: -0.0001

Data Index: 121444 (C4 (Web Text))

Max Activating Token Index: 914

Text #1

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.1160. Min Act: -0.0000

Data Index: 117651 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.1121. Min Act: -0.0000

Data Index: 661845 (C4 (Web Text))

Max Activating Token Index: 398

Text #3

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.1093. Min Act: -0.0001

Data Index: 1264434 (C4 (Web Text))

Max Activating Token Index: 309

Text #4

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.1041. Min Act: -0.0000

Data Index: 1625259 (Python Code)

Max Activating Token Index: 56

Text #5

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.1114. Min Act: -0.0000

Data Index: 1639588 (Python Code)

Max Activating Token Index: 784

Text #6

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.1004. Min Act: -0.0000

Data Index: 1122369 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.0976. Min Act: -0.0000

Data Index: 672421 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.0963. Min Act: -0.0000

Data Index: 1381841 (Python Code)

Max Activating Token Index: 227

Text #9

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.0972. Min Act: -0.0000

Data Index: 1514505 (Python Code)

Max Activating Token Index: 13

Text #10

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.0986. Min Act: -0.0000

Data Index: 1494657 (Python Code)

Max Activating Token Index: 657

Text #11

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.0916. Min Act: -0.0000

Data Index: 758076 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.0900. Min Act: -0.0000

Data Index: 646628 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.0933. Min Act: -0.0001

Data Index: 1642570 (Python Code)

Max Activating Token Index: 224

Text #14

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.0894. Min Act: -0.0001

Data Index: 37825 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.0927. Min Act: -0.0000

Data Index: 12461 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.0912. Min Act: -0.0001

Data Index: 466052 (C4 (Web Text))

Max Activating Token Index: 370

Text #17

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.0900. Min Act: -0.0000

Data Index: 1401105 (Python Code)

Max Activating Token Index: 521

Text #18

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.0896. Min Act: -0.0000

Data Index: 1422111 (Python Code)

Max Activating Token Index: 675

Text #19

Max Range: 0.1173. Min Range: -0.1173

Max Act: 0.0895. Min Act: -0.0000

Data Index: 1559282 (Python Code)

Max Activating Token Index: 156