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

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

Neuron 3225 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.5785. Min Act: -0.0000

Data Index: 1538076 (Python Code)

Max Activating Token Index: 151

Text #1

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.4107. Min Act: -0.0000

Data Index: 964155 (C4 (Web Text))

Max Activating Token Index: 151

Text #2

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.3808. Min Act: -0.0000

Data Index: 1047706 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.4553. Min Act: -0.0000

Data Index: 1379398 (Python Code)

Max Activating Token Index: 294

Text #4

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.3857. Min Act: -0.0000

Data Index: 866767 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.4100. Min Act: -0.0000

Data Index: 1542655 (Python Code)

Max Activating Token Index: 311

Text #6

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.3480. Min Act: -0.0000

Data Index: 214679 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.3228. Min Act: -0.0000

Data Index: 1456240 (Python Code)

Max Activating Token Index: 748

Text #8

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.3401. Min Act: -0.0000

Data Index: 165128 (C4 (Web Text))

Max Activating Token Index: 571

Text #9

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.3326. Min Act: -0.0000

Data Index: 1378685 (Python Code)

Max Activating Token Index: 990

Text #10

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.3219. Min Act: -0.0000

Data Index: 1617608 (Python Code)

Max Activating Token Index: 108

Text #11

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.2742. Min Act: -0.0000

Data Index: 936845 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.3359. Min Act: -0.0000

Data Index: 439833 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.2789. Min Act: -0.0000

Data Index: 1244493 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.2687. Min Act: -0.0000

Data Index: 312678 (C4 (Web Text))

Max Activating Token Index: 941

Text #15

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.2898. Min Act: -0.0000

Data Index: 786327 (C4 (Web Text))

Max Activating Token Index: 508

Text #16

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.2762. Min Act: -0.0000

Data Index: 115944 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.2281. Min Act: -0.0000

Data Index: 1094777 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.2473. Min Act: -0.0000

Data Index: 1268715 (C4 (Web Text))

Max Activating Token Index: 550

Text #19

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.2933. Min Act: -0.0000

Data Index: 1255438 (C4 (Web Text))

Max Activating Token Index: 126