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

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

Neuron 2555 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2985. Min Act: -0.0000

Data Index: 659999 (C4 (Web Text))

Max Activating Token Index: 550

Text #1

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2731. Min Act: -0.0000

Data Index: 476250 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2334. Min Act: -0.0000

Data Index: 860541 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2334. Min Act: -0.0000

Data Index: 295535 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2265. Min Act: -0.0000

Data Index: 13894 (C4 (Web Text))

Max Activating Token Index: 141

Text #5

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2143. Min Act: -0.0000

Data Index: 541562 (C4 (Web Text))

Max Activating Token Index: 1022

Text #6

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2251. Min Act: -0.0000

Data Index: 1346472 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2059. Min Act: -0.0000

Data Index: 1127997 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.1969. Min Act: -0.0000

Data Index: 1261917 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2120. Min Act: -0.0000

Data Index: 444690 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2102. Min Act: -0.0000

Data Index: 389272 (C4 (Web Text))

Max Activating Token Index: 260

Text #11

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2099. Min Act: -0.0000

Data Index: 476707 (C4 (Web Text))

Max Activating Token Index: 304

Text #12

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2099. Min Act: -0.0000

Data Index: 600000 (C4 (Web Text))

Max Activating Token Index: 956

Text #13

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2085. Min Act: -0.0000

Data Index: 566956 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2059. Min Act: -0.0000

Data Index: 1250043 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.1916. Min Act: -0.0000

Data Index: 88535 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.1983. Min Act: -0.0000

Data Index: 357712 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.2079. Min Act: -0.0000

Data Index: 157834 (C4 (Web Text))

Max Activating Token Index: 144

Text #18

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.1898. Min Act: -0.0000

Data Index: 390002 (C4 (Web Text))

Max Activating Token Index: 670

Text #19

Max Range: 0.2985. Min Range: -0.2985

Max Act: 0.1874. Min Act: -0.0000

Data Index: 397399 (C4 (Web Text))

Max Activating Token Index: 753