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

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

Neuron 4398 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: 2.7725. Min Range: -2.7725

Max Act: 2.7725. Min Act: -0.0002

Data Index: 142178 (C4 (Web Text))

Max Activating Token Index: 841

Text #1

Max Range: 2.7725. Min Range: -2.7725

Max Act: 2.7299. Min Act: -0.0002

Data Index: 717171 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 2.7725. Min Range: -2.7725

Max Act: 2.6410. Min Act: -0.0002

Data Index: 928864 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 2.7725. Min Range: -2.7725

Max Act: 2.6898. Min Act: -0.0002

Data Index: 216755 (C4 (Web Text))

Max Activating Token Index: 848

Text #4

Max Range: 2.7725. Min Range: -2.7725

Max Act: 2.6234. Min Act: -0.0002

Data Index: 286604 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 2.7725. Min Range: -2.7725

Max Act: 2.6500. Min Act: -0.0002

Data Index: 1292966 (C4 (Web Text))

Max Activating Token Index: 251

Text #6

Max Range: 2.7725. Min Range: -2.7725

Max Act: 2.6789. Min Act: -0.0002

Data Index: 1017184 (C4 (Web Text))

Max Activating Token Index: 630

Text #7

Max Range: 2.7725. Min Range: -2.7725

Max Act: 2.5386. Min Act: -0.0002

Data Index: 406668 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 2.7725. Min Range: -2.7725

Max Act: 2.5153. Min Act: -0.0002

Data Index: 1315579 (C4 (Web Text))

Max Activating Token Index: 914

Text #9

Max Range: 2.7725. Min Range: -2.7725

Max Act: 2.5179. Min Act: -0.0002

Data Index: 1357584 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 2.7725. Min Range: -2.7725

Max Act: 2.4671. Min Act: -0.0002

Data Index: 1213265 (C4 (Web Text))

Max Activating Token Index: 4

Text #11

Max Range: 2.7725. Min Range: -2.7725

Max Act: 2.5968. Min Act: -0.0002

Data Index: 1266850 (C4 (Web Text))

Max Activating Token Index: 690

Text #12

Max Range: 2.7725. Min Range: -2.7725

Max Act: 2.5659. Min Act: -0.0002

Data Index: 1176598 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 2.7725. Min Range: -2.7725

Max Act: 2.4946. Min Act: -0.0002

Data Index: 912157 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 2.7725. Min Range: -2.7725

Max Act: 2.5232. Min Act: -0.0002

Data Index: 658552 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 2.7725. Min Range: -2.7725

Max Act: 2.4573. Min Act: -0.0002

Data Index: 583705 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 2.7725. Min Range: -2.7725

Max Act: 2.4760. Min Act: -0.0002

Data Index: 228384 (C4 (Web Text))

Max Activating Token Index: 711

Text #17

Max Range: 2.7725. Min Range: -2.7725

Max Act: 2.4310. Min Act: -0.0002

Data Index: 700295 (C4 (Web Text))

Max Activating Token Index: 960

Text #18

Max Range: 2.7725. Min Range: -2.7725

Max Act: 2.4592. Min Act: -0.0002

Data Index: 183955 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 2.7725. Min Range: -2.7725

Max Act: 2.4475. Min Act: -0.0002

Data Index: 955354 (C4 (Web Text))

Max Activating Token Index: 622