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

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

Neuron 2900 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9288. Min Range: -0.9288

Max Act: 0.9179. Min Act: -0.0000

Data Index: 1128767 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 0.9288. Min Range: -0.9288

Max Act: 0.9199. Min Act: -0.0000

Data Index: 818235 (C4 (Web Text))

Max Activating Token Index: 867

Text #2

Max Range: 0.9288. Min Range: -0.9288

Max Act: 0.9288. Min Act: -0.0000

Data Index: 428530 (C4 (Web Text))

Max Activating Token Index: 186

Text #3

Max Range: 0.9288. Min Range: -0.9288

Max Act: 0.8907. Min Act: -0.0000

Data Index: 1438099 (Python Code)

Max Activating Token Index: 1005

Text #4

Max Range: 0.9288. Min Range: -0.9288

Max Act: 0.9206. Min Act: -0.0000

Data Index: 258501 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 0.9288. Min Range: -0.9288

Max Act: 0.8205. Min Act: -0.0000

Data Index: 653015 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 0.9288. Min Range: -0.9288

Max Act: 0.7900. Min Act: -0.0000

Data Index: 1079596 (C4 (Web Text))

Max Activating Token Index: 601

Text #7

Max Range: 0.9288. Min Range: -0.9288

Max Act: 0.8322. Min Act: -0.0000

Data Index: 1529153 (Python Code)

Max Activating Token Index: 146

Text #8

Max Range: 0.9288. Min Range: -0.9288

Max Act: 0.8251. Min Act: -0.0000

Data Index: 1441822 (Python Code)

Max Activating Token Index: 864

Text #9

Max Range: 0.9288. Min Range: -0.9288

Max Act: 0.8246. Min Act: -0.0000

Data Index: 586225 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 0.9288. Min Range: -0.9288

Max Act: 0.7858. Min Act: -0.0000

Data Index: 955289 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 0.9288. Min Range: -0.9288

Max Act: 0.7763. Min Act: -0.0000

Data Index: 861657 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 0.9288. Min Range: -0.9288

Max Act: 0.7980. Min Act: -0.0000

Data Index: 209529 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 0.9288. Min Range: -0.9288

Max Act: 0.7419. Min Act: -0.0000

Data Index: 817959 (C4 (Web Text))

Max Activating Token Index: 587

Text #14

Max Range: 0.9288. Min Range: -0.9288

Max Act: 0.8075. Min Act: -0.0000

Data Index: 953987 (C4 (Web Text))

Max Activating Token Index: 622

Text #15

Max Range: 0.9288. Min Range: -0.9288

Max Act: 0.7375. Min Act: -0.0000

Data Index: 1157966 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 0.9288. Min Range: -0.9288

Max Act: 0.7267. Min Act: -0.0000

Data Index: 918989 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 0.9288. Min Range: -0.9288

Max Act: 0.7284. Min Act: -0.0000

Data Index: 483027 (C4 (Web Text))

Max Activating Token Index: 818

Text #18

Max Range: 0.9288. Min Range: -0.9288

Max Act: 0.7462. Min Act: -0.0000

Data Index: 554549 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 0.9288. Min Range: -0.9288

Max Act: 0.7955. Min Act: -0.0000

Data Index: 1299874 (C4 (Web Text))

Max Activating Token Index: 326