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

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

Neuron 4181 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: 2.0426. Min Range: -2.0426

Max Act: 2.0426. Min Act: -0.0002

Data Index: 167462 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 2.0426. Min Range: -2.0426

Max Act: 2.0385. Min Act: -0.0002

Data Index: 458528 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 2.0426. Min Range: -2.0426

Max Act: 1.9307. Min Act: -0.0002

Data Index: 1312932 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 2.0426. Min Range: -2.0426

Max Act: 1.9740. Min Act: -0.0002

Data Index: 1344085 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 2.0426. Min Range: -2.0426

Max Act: 1.9255. Min Act: -0.0002

Data Index: 41625 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 2.0426. Min Range: -2.0426

Max Act: 1.9743. Min Act: -0.0002

Data Index: 938609 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 2.0426. Min Range: -2.0426

Max Act: 1.9083. Min Act: -0.0002

Data Index: 50800 (C4 (Web Text))

Max Activating Token Index: 669

Text #7

Max Range: 2.0426. Min Range: -2.0426

Max Act: 1.9789. Min Act: -0.0002

Data Index: 1077658 (C4 (Web Text))

Max Activating Token Index: 849

Text #8

Max Range: 2.0426. Min Range: -2.0426

Max Act: 1.9199. Min Act: -0.0002

Data Index: 401841 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 2.0426. Min Range: -2.0426

Max Act: 1.8952. Min Act: -0.0002

Data Index: 716529 (C4 (Web Text))

Max Activating Token Index: 248

Text #10

Max Range: 2.0426. Min Range: -2.0426

Max Act: 1.8630. Min Act: -0.0002

Data Index: 1257801 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 2.0426. Min Range: -2.0426

Max Act: 1.9428. Min Act: -0.0002

Data Index: 115332 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 2.0426. Min Range: -2.0426

Max Act: 1.9232. Min Act: -0.0002

Data Index: 1124440 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 2.0426. Min Range: -2.0426

Max Act: 1.9568. Min Act: -0.0002

Data Index: 1159195 (C4 (Web Text))

Max Activating Token Index: 395

Text #14

Max Range: 2.0426. Min Range: -2.0426

Max Act: 1.9426. Min Act: -0.0002

Data Index: 326264 (C4 (Web Text))

Max Activating Token Index: 765

Text #15

Max Range: 2.0426. Min Range: -2.0426

Max Act: 1.9103. Min Act: -0.0002

Data Index: 1126903 (C4 (Web Text))

Max Activating Token Index: 3

Text #16

Max Range: 2.0426. Min Range: -2.0426

Max Act: 1.8509. Min Act: -0.0002

Data Index: 785455 (C4 (Web Text))

Max Activating Token Index: 788

Text #17

Max Range: 2.0426. Min Range: -2.0426

Max Act: 1.8478. Min Act: -0.0002

Data Index: 917762 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 2.0426. Min Range: -2.0426

Max Act: 1.8579. Min Act: -0.0002

Data Index: 1340616 (C4 (Web Text))

Max Activating Token Index: 652

Text #19

Max Range: 2.0426. Min Range: -2.0426

Max Act: 1.8796. Min Act: -0.0002

Data Index: 799378 (C4 (Web Text))

Max Activating Token Index: 886