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

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

Neuron 1816 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: 0.2512. Min Range: -0.2512

Max Act: 0.2512. Min Act: -0.0000

Data Index: 1209938 (C4 (Web Text))

Max Activating Token Index: 889

Text #1

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.1624. Min Act: -0.0000

Data Index: 272667 (C4 (Web Text))

Max Activating Token Index: 724

Text #2

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.1566. Min Act: -0.0000

Data Index: 488974 (C4 (Web Text))

Max Activating Token Index: 921

Text #3

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.1676. Min Act: -0.0000

Data Index: 317992 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.1611. Min Act: -0.0000

Data Index: 73266 (C4 (Web Text))

Max Activating Token Index: 337

Text #5

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.1445. Min Act: -0.0000

Data Index: 101213 (C4 (Web Text))

Max Activating Token Index: 653

Text #6

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.1409. Min Act: -0.0000

Data Index: 1061579 (C4 (Web Text))

Max Activating Token Index: 683

Text #7

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.1429. Min Act: 0.0000

Data Index: 135480 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.1368. Min Act: -0.0000

Data Index: 637873 (C4 (Web Text))

Max Activating Token Index: 609

Text #9

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.1301. Min Act: -0.0000

Data Index: 482900 (C4 (Web Text))

Max Activating Token Index: 671

Text #10

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.1287. Min Act: -0.0000

Data Index: 636810 (C4 (Web Text))

Max Activating Token Index: 922

Text #11

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.1290. Min Act: -0.0000

Data Index: 1140268 (C4 (Web Text))

Max Activating Token Index: 831

Text #12

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.1205. Min Act: -0.0000

Data Index: 277181 (C4 (Web Text))

Max Activating Token Index: 669

Text #13

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.1136. Min Act: -0.0000

Data Index: 1312905 (C4 (Web Text))

Max Activating Token Index: 110

Text #14

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.1120. Min Act: -0.0000

Data Index: 1154092 (C4 (Web Text))

Max Activating Token Index: 917

Text #15

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.1209. Min Act: -0.0000

Data Index: 159598 (C4 (Web Text))

Max Activating Token Index: 643

Text #16

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.1202. Min Act: -0.0000

Data Index: 1248630 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.1197. Min Act: -0.0000

Data Index: 699870 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.1142. Min Act: -0.0000

Data Index: 43333 (C4 (Web Text))

Max Activating Token Index: 1006

Text #19

Max Range: 0.2512. Min Range: -0.2512

Max Act: 0.1160. Min Act: -0.0000

Data Index: 1061756 (C4 (Web Text))

Max Activating Token Index: 93