Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 828 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2377. Min Range: -1.2377

Max Act: 1.2377. Min Act: -0.0000

Data Index: 663153 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 1.2377. Min Range: -1.2377

Max Act: 1.2304. Min Act: -0.0000

Data Index: 165009 (C4 (Web Text))

Max Activating Token Index: 410

Text #2

Max Range: 1.2377. Min Range: -1.2377

Max Act: 1.1009. Min Act: -0.0001

Data Index: 524272 (C4 (Web Text))

Max Activating Token Index: 774

Text #3

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.9952. Min Act: -0.0000

Data Index: 934191 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.9594. Min Act: -0.0001

Data Index: 972611 (C4 (Web Text))

Max Activating Token Index: 884

Text #5

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.9555. Min Act: -0.0000

Data Index: 747523 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.9793. Min Act: -0.0000

Data Index: 789676 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.9011. Min Act: -0.0001

Data Index: 166154 (C4 (Web Text))

Max Activating Token Index: 657

Text #8

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.9559. Min Act: -0.0000

Data Index: 1010484 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.9169. Min Act: -0.0000

Data Index: 1167369 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.8970. Min Act: -0.0000

Data Index: 1048550 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.8990. Min Act: 0.0000

Data Index: 954125 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.8697. Min Act: -0.0001

Data Index: 336414 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.8371. Min Act: 0.0001

Data Index: 164195 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.8291. Min Act: -0.0001

Data Index: 281499 (C4 (Web Text))

Max Activating Token Index: 354

Text #15

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.8492. Min Act: 0.0002

Data Index: 86675 (C4 (Web Text))

Max Activating Token Index: 528

Text #16

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.8155. Min Act: -0.0000

Data Index: 961907 (C4 (Web Text))

Max Activating Token Index: 972

Text #17

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.8405. Min Act: -0.0000

Data Index: 273568 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.8146. Min Act: -0.0000

Data Index: 372184 (C4 (Web Text))

Max Activating Token Index: 316

Text #19

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.8040. Min Act: -0.0000

Data Index: 1300046 (C4 (Web Text))

Max Activating Token Index: 212