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

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

Neuron 2586 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: 1.1736. Min Range: -1.1736

Max Act: 1.1327. Min Act: -0.0000

Data Index: 192721 (C4 (Web Text))

Max Activating Token Index: 552

Text #1

Max Range: 1.1736. Min Range: -1.1736

Max Act: 1.0897. Min Act: -0.0000

Data Index: 390366 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 1.1736. Min Range: -1.1736

Max Act: 1.1736. Min Act: -0.0000

Data Index: 243990 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 1.1736. Min Range: -1.1736

Max Act: 1.0580. Min Act: -0.0000

Data Index: 229246 (C4 (Web Text))

Max Activating Token Index: 949

Text #4

Max Range: 1.1736. Min Range: -1.1736

Max Act: 1.0854. Min Act: -0.0000

Data Index: 1301379 (C4 (Web Text))

Max Activating Token Index: 949

Text #5

Max Range: 1.1736. Min Range: -1.1736

Max Act: 1.0540. Min Act: -0.0000

Data Index: 1001083 (C4 (Web Text))

Max Activating Token Index: 416

Text #6

Max Range: 1.1736. Min Range: -1.1736

Max Act: 1.0204. Min Act: -0.0000

Data Index: 1178102 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 1.1736. Min Range: -1.1736

Max Act: 1.0067. Min Act: -0.0000

Data Index: 404262 (C4 (Web Text))

Max Activating Token Index: 317

Text #8

Max Range: 1.1736. Min Range: -1.1736

Max Act: 1.0248. Min Act: -0.0000

Data Index: 559078 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 1.1736. Min Range: -1.1736

Max Act: 0.9975. Min Act: -0.0000

Data Index: 98867 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 1.1736. Min Range: -1.1736

Max Act: 0.9983. Min Act: -0.0000

Data Index: 1284406 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 1.1736. Min Range: -1.1736

Max Act: 0.9686. Min Act: -0.0000

Data Index: 404227 (C4 (Web Text))

Max Activating Token Index: 537

Text #12

Max Range: 1.1736. Min Range: -1.1736

Max Act: 0.9617. Min Act: -0.0000

Data Index: 590941 (C4 (Web Text))

Max Activating Token Index: 909

Text #13

Max Range: 1.1736. Min Range: -1.1736

Max Act: 0.9698. Min Act: -0.0000

Data Index: 1250323 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 1.1736. Min Range: -1.1736

Max Act: 0.9493. Min Act: -0.0000

Data Index: 609263 (C4 (Web Text))

Max Activating Token Index: 802

Text #15

Max Range: 1.1736. Min Range: -1.1736

Max Act: 0.9845. Min Act: -0.0000

Data Index: 116420 (C4 (Web Text))

Max Activating Token Index: 448

Text #16

Max Range: 1.1736. Min Range: -1.1736

Max Act: 0.9237. Min Act: -0.0000

Data Index: 1162920 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 1.1736. Min Range: -1.1736

Max Act: 0.9146. Min Act: -0.0000

Data Index: 135352 (C4 (Web Text))

Max Activating Token Index: 934

Text #18

Max Range: 1.1736. Min Range: -1.1736

Max Act: 0.9725. Min Act: -0.0000

Data Index: 1165170 (C4 (Web Text))

Max Activating Token Index: 710

Text #19

Max Range: 1.1736. Min Range: -1.1736

Max Act: 0.9328. Min Act: -0.0000

Data Index: 542060 (C4 (Web Text))

Max Activating Token Index: 943