Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2119 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.2528. Min Act: -0.0000

Data Index: 1564015 (Python Code)

Max Activating Token Index: 613

Text #1

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.1616. Min Act: -0.0000

Data Index: 530868 (C4 (Web Text))

Max Activating Token Index: 971

Text #2

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.1332. Min Act: -0.0000

Data Index: 1478433 (Python Code)

Max Activating Token Index: 439

Text #3

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.1339. Min Act: -0.0000

Data Index: 1071533 (C4 (Web Text))

Max Activating Token Index: 1010

Text #4

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.1312. Min Act: -0.0000

Data Index: 226007 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.1337. Min Act: -0.0000

Data Index: 880836 (C4 (Web Text))

Max Activating Token Index: 882

Text #6

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.1201. Min Act: -0.0000

Data Index: 107018 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.1201. Min Act: -0.0000

Data Index: 241443 (C4 (Web Text))

Max Activating Token Index: 947

Text #8

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.1173. Min Act: -0.0000

Data Index: 1615405 (Python Code)

Max Activating Token Index: 216

Text #9

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.1181. Min Act: -0.0000

Data Index: 1148648 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.1140. Min Act: -0.0000

Data Index: 1619567 (Python Code)

Max Activating Token Index: 889

Text #11

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.1155. Min Act: -0.0000

Data Index: 1349964 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.1192. Min Act: -0.0000

Data Index: 603537 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.1222. Min Act: -0.0000

Data Index: 267503 (C4 (Web Text))

Max Activating Token Index: 454

Text #14

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.1174. Min Act: -0.0000

Data Index: 740145 (C4 (Web Text))

Max Activating Token Index: 938

Text #15

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.1120. Min Act: -0.0000

Data Index: 1426715 (Python Code)

Max Activating Token Index: 432

Text #16

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.1241. Min Act: -0.0000

Data Index: 1097753 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.1151. Min Act: -0.0000

Data Index: 32047 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.1064. Min Act: -0.0000

Data Index: 200916 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 0.2528. Min Range: -0.2528

Max Act: 0.1184. Min Act: -0.0000

Data Index: 1606387 (Python Code)

Max Activating Token Index: 804