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

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

Neuron 1092 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4513. Min Range: -2.4513

Max Act: 2.4513. Min Act: -0.0000

Data Index: 419153 (C4 (Web Text))

Max Activating Token Index: 671

Text #1

Max Range: 2.4513. Min Range: -2.4513

Max Act: 2.3220. Min Act: -0.0000

Data Index: 489003 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 2.4513. Min Range: -2.4513

Max Act: 2.3840. Min Act: -0.0000

Data Index: 419506 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 2.4513. Min Range: -2.4513

Max Act: 2.3592. Min Act: -0.0000

Data Index: 220959 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 2.4513. Min Range: -2.4513

Max Act: 2.4196. Min Act: -0.0000

Data Index: 212378 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 2.4513. Min Range: -2.4513

Max Act: 2.1720. Min Act: -0.0000

Data Index: 70871 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 2.4513. Min Range: -2.4513

Max Act: 1.7260. Min Act: -0.0000

Data Index: 452643 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 2.4513. Min Range: -2.4513

Max Act: 1.8136. Min Act: -0.0000

Data Index: 902607 (C4 (Web Text))

Max Activating Token Index: 1007

Text #8

Max Range: 2.4513. Min Range: -2.4513

Max Act: 1.7166. Min Act: -0.0000

Data Index: 996626 (C4 (Web Text))

Max Activating Token Index: 741

Text #9

Max Range: 2.4513. Min Range: -2.4513

Max Act: 1.4696. Min Act: -0.0000

Data Index: 243004 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 2.4513. Min Range: -2.4513

Max Act: 1.5002. Min Act: -0.0000

Data Index: 444639 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 2.4513. Min Range: -2.4513

Max Act: 1.4727. Min Act: -0.0000

Data Index: 216862 (C4 (Web Text))

Max Activating Token Index: 944

Text #12

Max Range: 2.4513. Min Range: -2.4513

Max Act: 1.4949. Min Act: -0.0000

Data Index: 269614 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 2.4513. Min Range: -2.4513

Max Act: 1.4148. Min Act: -0.0000

Data Index: 1322184 (C4 (Web Text))

Max Activating Token Index: 1022

Text #14

Max Range: 2.4513. Min Range: -2.4513

Max Act: 1.4857. Min Act: -0.0000

Data Index: 419593 (C4 (Web Text))

Max Activating Token Index: 568

Text #15

Max Range: 2.4513. Min Range: -2.4513

Max Act: 1.3034. Min Act: -0.0000

Data Index: 968706 (C4 (Web Text))

Max Activating Token Index: 992

Text #16

Max Range: 2.4513. Min Range: -2.4513

Max Act: 1.4051. Min Act: -0.0000

Data Index: 1154498 (C4 (Web Text))

Max Activating Token Index: 517

Text #17

Max Range: 2.4513. Min Range: -2.4513

Max Act: 1.3329. Min Act: -0.0000

Data Index: 400593 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 2.4513. Min Range: -2.4513

Max Act: 1.3621. Min Act: -0.0000

Data Index: 320273 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 2.4513. Min Range: -2.4513

Max Act: 1.3157. Min Act: -0.0000

Data Index: 1291473 (C4 (Web Text))

Max Activating Token Index: 363