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

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

Neuron 1833 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.1666. Min Range: -2.1666

Max Act: 2.1666. Min Act: -0.0002

Data Index: 423206 (C4 (Web Text))

Max Activating Token Index: 666

Text #1

Max Range: 2.1666. Min Range: -2.1666

Max Act: 2.0578. Min Act: -0.0002

Data Index: 1051489 (C4 (Web Text))

Max Activating Token Index: 960

Text #2

Max Range: 2.1666. Min Range: -2.1666

Max Act: 2.0596. Min Act: -0.0002

Data Index: 603308 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 2.1666. Min Range: -2.1666

Max Act: 1.8580. Min Act: -0.0002

Data Index: 425364 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 2.1666. Min Range: -2.1666

Max Act: 1.7519. Min Act: -0.0002

Data Index: 650431 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 2.1666. Min Range: -2.1666

Max Act: 1.7149. Min Act: -0.0002

Data Index: 563104 (C4 (Web Text))

Max Activating Token Index: 649

Text #6

Max Range: 2.1666. Min Range: -2.1666

Max Act: 1.7388. Min Act: -0.0002

Data Index: 10202 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 2.1666. Min Range: -2.1666

Max Act: 1.7273. Min Act: -0.0003

Data Index: 1122311 (C4 (Web Text))

Max Activating Token Index: 906

Text #8

Max Range: 2.1666. Min Range: -2.1666

Max Act: 1.7920. Min Act: -0.0002

Data Index: 782493 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 2.1666. Min Range: -2.1666

Max Act: 1.6644. Min Act: -0.0002

Data Index: 1080532 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 2.1666. Min Range: -2.1666

Max Act: 1.6421. Min Act: -0.0002

Data Index: 1304047 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 2.1666. Min Range: -2.1666

Max Act: 1.7034. Min Act: -0.0002

Data Index: 224077 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 2.1666. Min Range: -2.1666

Max Act: 1.6492. Min Act: -0.0002

Data Index: 91130 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 2.1666. Min Range: -2.1666

Max Act: 1.6416. Min Act: -0.0002

Data Index: 1073522 (C4 (Web Text))

Max Activating Token Index: 671

Text #14

Max Range: 2.1666. Min Range: -2.1666

Max Act: 1.6489. Min Act: -0.0003

Data Index: 944711 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 2.1666. Min Range: -2.1666

Max Act: 1.6393. Min Act: -0.0002

Data Index: 844420 (C4 (Web Text))

Max Activating Token Index: 838

Text #16

Max Range: 2.1666. Min Range: -2.1666

Max Act: 1.6835. Min Act: -0.0002

Data Index: 97558 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 2.1666. Min Range: -2.1666

Max Act: 1.6079. Min Act: -0.0002

Data Index: 1013576 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 2.1666. Min Range: -2.1666

Max Act: 1.6179. Min Act: -0.0002

Data Index: 1251297 (C4 (Web Text))

Max Activating Token Index: 922

Text #19

Max Range: 2.1666. Min Range: -2.1666

Max Act: 1.6228. Min Act: -0.0002

Data Index: 446651 (C4 (Web Text))

Max Activating Token Index: 731