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

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

Neuron 456 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6749. Min Range: -2.6749

Max Act: 2.5812. Min Act: -0.0000

Data Index: 1173244 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 2.6749. Min Range: -2.6749

Max Act: 2.6749. Min Act: -0.0000

Data Index: 663491 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 2.6749. Min Range: -2.6749

Max Act: 2.4334. Min Act: -0.0000

Data Index: 800423 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 2.6749. Min Range: -2.6749

Max Act: 2.5237. Min Act: -0.0000

Data Index: 1137075 (C4 (Web Text))

Max Activating Token Index: 674

Text #4

Max Range: 2.6749. Min Range: -2.6749

Max Act: 2.4950. Min Act: -0.0000

Data Index: 59786 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 2.6749. Min Range: -2.6749

Max Act: 2.4693. Min Act: -0.0000

Data Index: 821457 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 2.6749. Min Range: -2.6749

Max Act: 2.2175. Min Act: -0.0000

Data Index: 578013 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 2.6749. Min Range: -2.6749

Max Act: 2.1475. Min Act: -0.0000

Data Index: 216205 (C4 (Web Text))

Max Activating Token Index: 834

Text #8

Max Range: 2.6749. Min Range: -2.6749

Max Act: 2.0026. Min Act: -0.0000

Data Index: 387367 (C4 (Web Text))

Max Activating Token Index: 565

Text #9

Max Range: 2.6749. Min Range: -2.6749

Max Act: 2.0610. Min Act: -0.0000

Data Index: 42300 (C4 (Web Text))

Max Activating Token Index: 337

Text #10

Max Range: 2.6749. Min Range: -2.6749

Max Act: 1.9181. Min Act: -0.0000

Data Index: 1355456 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 2.6749. Min Range: -2.6749

Max Act: 1.9789. Min Act: -0.0000

Data Index: 1013021 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 2.6749. Min Range: -2.6749

Max Act: 1.8630. Min Act: -0.0000

Data Index: 626794 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 2.6749. Min Range: -2.6749

Max Act: 2.0545. Min Act: -0.0000

Data Index: 454842 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 2.6749. Min Range: -2.6749

Max Act: 1.9552. Min Act: -0.0000

Data Index: 708464 (C4 (Web Text))

Max Activating Token Index: 810

Text #15

Max Range: 2.6749. Min Range: -2.6749

Max Act: 1.9402. Min Act: -0.0000

Data Index: 313655 (C4 (Web Text))

Max Activating Token Index: 653

Text #16

Max Range: 2.6749. Min Range: -2.6749

Max Act: 1.9206. Min Act: -0.0000

Data Index: 1104632 (C4 (Web Text))

Max Activating Token Index: 553

Text #17

Max Range: 2.6749. Min Range: -2.6749

Max Act: 1.8885. Min Act: -0.0000

Data Index: 1161662 (C4 (Web Text))

Max Activating Token Index: 216

Text #18

Max Range: 2.6749. Min Range: -2.6749

Max Act: 1.8706. Min Act: -0.0000

Data Index: 356521 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 2.6749. Min Range: -2.6749

Max Act: 1.8581. Min Act: -0.0000

Data Index: 1121605 (C4 (Web Text))

Max Activating Token Index: 953