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

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

Neuron 996 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9085. Min Range: -0.9085

Max Act: 0.9085. Min Act: -0.0001

Data Index: 1327057 (C4 (Web Text))

Max Activating Token Index: 486

Text #1

Max Range: 0.9085. Min Range: -0.9085

Max Act: 0.8798. Min Act: -0.0001

Data Index: 118382 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 0.9085. Min Range: -0.9085

Max Act: 0.7965. Min Act: -0.0001

Data Index: 29192 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 0.9085. Min Range: -0.9085

Max Act: 0.8033. Min Act: -0.0001

Data Index: 1570274 (Python Code)

Max Activating Token Index: 289

Text #4

Max Range: 0.9085. Min Range: -0.9085

Max Act: 0.7564. Min Act: -0.0001

Data Index: 1444458 (Python Code)

Max Activating Token Index: 85

Text #5

Max Range: 0.9085. Min Range: -0.9085

Max Act: 0.8423. Min Act: -0.0001

Data Index: 524217 (C4 (Web Text))

Max Activating Token Index: 85

Text #6

Max Range: 0.9085. Min Range: -0.9085

Max Act: 0.6766. Min Act: -0.0001

Data Index: 177455 (C4 (Web Text))

Max Activating Token Index: 710

Text #7

Max Range: 0.9085. Min Range: -0.9085

Max Act: 0.7998. Min Act: -0.0001

Data Index: 657218 (C4 (Web Text))

Max Activating Token Index: 963

Text #8

Max Range: 0.9085. Min Range: -0.9085

Max Act: 0.7319. Min Act: -0.0001

Data Index: 714984 (C4 (Web Text))

Max Activating Token Index: 193

Text #9

Max Range: 0.9085. Min Range: -0.9085

Max Act: 0.7640. Min Act: -0.0001

Data Index: 551199 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 0.9085. Min Range: -0.9085

Max Act: 0.7480. Min Act: -0.0001

Data Index: 1485111 (Python Code)

Max Activating Token Index: 436

Text #11

Max Range: 0.9085. Min Range: -0.9085

Max Act: 0.6919. Min Act: -0.0001

Data Index: 101792 (C4 (Web Text))

Max Activating Token Index: 608

Text #12

Max Range: 0.9085. Min Range: -0.9085

Max Act: 0.7318. Min Act: -0.0001

Data Index: 610534 (C4 (Web Text))

Max Activating Token Index: 4

Text #13

Max Range: 0.9085. Min Range: -0.9085

Max Act: 0.7131. Min Act: -0.0001

Data Index: 674988 (C4 (Web Text))

Max Activating Token Index: 5

Text #14

Max Range: 0.9085. Min Range: -0.9085

Max Act: 0.7748. Min Act: -0.0001

Data Index: 34911 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 0.9085. Min Range: -0.9085

Max Act: 0.6931. Min Act: -0.0001

Data Index: 430920 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 0.9085. Min Range: -0.9085

Max Act: 0.7309. Min Act: -0.0001

Data Index: 1424112 (Python Code)

Max Activating Token Index: 939

Text #17

Max Range: 0.9085. Min Range: -0.9085

Max Act: 0.7167. Min Act: -0.0001

Data Index: 991443 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 0.9085. Min Range: -0.9085

Max Act: 0.8961. Min Act: -0.0001

Data Index: 1553283 (Python Code)

Max Activating Token Index: 807

Text #19

Max Range: 0.9085. Min Range: -0.9085

Max Act: 0.7392. Min Act: -0.0001

Data Index: 543497 (C4 (Web Text))

Max Activating Token Index: 294