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

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

Neuron 1452 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.8443. Min Range: -7.8443

Max Act: 7.8443. Min Act: -0.0000

Data Index: 90418 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 7.8443. Min Range: -7.8443

Max Act: 7.4179. Min Act: -0.0000

Data Index: 281204 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 7.8443. Min Range: -7.8443

Max Act: 7.5158. Min Act: -0.0000

Data Index: 1128429 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 7.8443. Min Range: -7.8443

Max Act: 7.2340. Min Act: -0.0000

Data Index: 669514 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 7.8443. Min Range: -7.8443

Max Act: 7.2157. Min Act: -0.0000

Data Index: 1136077 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 7.8443. Min Range: -7.8443

Max Act: 7.5383. Min Act: -0.0000

Data Index: 1274376 (C4 (Web Text))

Max Activating Token Index: 643

Text #6

Max Range: 7.8443. Min Range: -7.8443

Max Act: 7.1278. Min Act: -0.0000

Data Index: 722043 (C4 (Web Text))

Max Activating Token Index: 924

Text #7

Max Range: 7.8443. Min Range: -7.8443

Max Act: 7.1509. Min Act: -0.0000

Data Index: 561595 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 7.8443. Min Range: -7.8443

Max Act: 7.1516. Min Act: -0.0000

Data Index: 324784 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 7.8443. Min Range: -7.8443

Max Act: 6.8940. Min Act: -0.0000

Data Index: 850708 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 7.8443. Min Range: -7.8443

Max Act: 7.4143. Min Act: -0.0000

Data Index: 722434 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 7.8443. Min Range: -7.8443

Max Act: 6.9094. Min Act: -0.0000

Data Index: 1054947 (C4 (Web Text))

Max Activating Token Index: 794

Text #12

Max Range: 7.8443. Min Range: -7.8443

Max Act: 6.3276. Min Act: -0.0000

Data Index: 684581 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 7.8443. Min Range: -7.8443

Max Act: 7.6514. Min Act: -0.0000

Data Index: 328392 (C4 (Web Text))

Max Activating Token Index: 347

Text #14

Max Range: 7.8443. Min Range: -7.8443

Max Act: 7.5566. Min Act: -0.0000

Data Index: 982183 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 7.8443. Min Range: -7.8443

Max Act: 6.7553. Min Act: -0.0000

Data Index: 1134690 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 7.8443. Min Range: -7.8443

Max Act: 6.5643. Min Act: -0.0000

Data Index: 1254246 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 7.8443. Min Range: -7.8443

Max Act: 6.7185. Min Act: -0.0000

Data Index: 1142905 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 7.8443. Min Range: -7.8443

Max Act: 6.5779. Min Act: -0.0000

Data Index: 275110 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 7.8443. Min Range: -7.8443

Max Act: 6.5117. Min Act: -0.0000

Data Index: 651836 (C4 (Web Text))

Max Activating Token Index: 786