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

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

Neuron 3151 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1856. Min Range: -0.1856

Max Act: 0.1708. Min Act: -0.0000

Data Index: 464282 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 0.1856. Min Range: -0.1856

Max Act: 0.1856. Min Act: -0.0000

Data Index: 645437 (C4 (Web Text))

Max Activating Token Index: 867

Text #2

Max Range: 0.1856. Min Range: -0.1856

Max Act: 0.1693. Min Act: -0.0000

Data Index: 383715 (C4 (Web Text))

Max Activating Token Index: 413

Text #3

Max Range: 0.1856. Min Range: -0.1856

Max Act: 0.1630. Min Act: -0.0000

Data Index: 882485 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 0.1856. Min Range: -0.1856

Max Act: 0.1490. Min Act: -0.0000

Data Index: 836298 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 0.1856. Min Range: -0.1856

Max Act: 0.1531. Min Act: -0.0000

Data Index: 603826 (C4 (Web Text))

Max Activating Token Index: 126

Text #6

Max Range: 0.1856. Min Range: -0.1856

Max Act: 0.1518. Min Act: -0.0000

Data Index: 146471 (C4 (Web Text))

Max Activating Token Index: 587

Text #7

Max Range: 0.1856. Min Range: -0.1856

Max Act: 0.1422. Min Act: -0.0000

Data Index: 269897 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 0.1856. Min Range: -0.1856

Max Act: 0.1426. Min Act: -0.0000

Data Index: 1490300 (Python Code)

Max Activating Token Index: 486

Text #9

Max Range: 0.1856. Min Range: -0.1856

Max Act: 0.1372. Min Act: -0.0000

Data Index: 1202840 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 0.1856. Min Range: -0.1856

Max Act: 0.1401. Min Act: -0.0000

Data Index: 68693 (C4 (Web Text))

Max Activating Token Index: 173

Text #11

Max Range: 0.1856. Min Range: -0.1856

Max Act: 0.1321. Min Act: -0.0000

Data Index: 1232584 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 0.1856. Min Range: -0.1856

Max Act: 0.1404. Min Act: -0.0000

Data Index: 1107343 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 0.1856. Min Range: -0.1856

Max Act: 0.1359. Min Act: -0.0000

Data Index: 937993 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 0.1856. Min Range: -0.1856

Max Act: 0.1240. Min Act: -0.0000

Data Index: 1454988 (Python Code)

Max Activating Token Index: 37

Text #15

Max Range: 0.1856. Min Range: -0.1856

Max Act: 0.1305. Min Act: -0.0000

Data Index: 1195058 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 0.1856. Min Range: -0.1856

Max Act: 0.1147. Min Act: -0.0000

Data Index: 801615 (C4 (Web Text))

Max Activating Token Index: 991

Text #17

Max Range: 0.1856. Min Range: -0.1856

Max Act: 0.1226. Min Act: -0.0000

Data Index: 205150 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 0.1856. Min Range: -0.1856

Max Act: 0.1093. Min Act: -0.0000

Data Index: 1232302 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 0.1856. Min Range: -0.1856

Max Act: 0.1182. Min Act: -0.0000

Data Index: 155863 (C4 (Web Text))

Max Activating Token Index: 828