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

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

Neuron 578 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6610. Min Range: -3.6610

Max Act: 3.6610. Min Act: -0.0001

Data Index: 1164580 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 3.6610. Min Range: -3.6610

Max Act: 3.0297. Min Act: -0.0001

Data Index: 587859 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 3.6610. Min Range: -3.6610

Max Act: 2.4590. Min Act: -0.0000

Data Index: 920124 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 3.6610. Min Range: -3.6610

Max Act: 2.3257. Min Act: -0.0001

Data Index: 418788 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 3.6610. Min Range: -3.6610

Max Act: 2.3277. Min Act: -0.0000

Data Index: 552834 (C4 (Web Text))

Max Activating Token Index: 974

Text #5

Max Range: 3.6610. Min Range: -3.6610

Max Act: 1.9611. Min Act: -0.0001

Data Index: 796297 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 3.6610. Min Range: -3.6610

Max Act: 2.3010. Min Act: -0.0001

Data Index: 657063 (C4 (Web Text))

Max Activating Token Index: 97

Text #7

Max Range: 3.6610. Min Range: -3.6610

Max Act: 1.9520. Min Act: -0.0001

Data Index: 1327236 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 3.6610. Min Range: -3.6610

Max Act: 2.1301. Min Act: -0.0001

Data Index: 74283 (C4 (Web Text))

Max Activating Token Index: 586

Text #9

Max Range: 3.6610. Min Range: -3.6610

Max Act: 1.6078. Min Act: -0.0001

Data Index: 258552 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 3.6610. Min Range: -3.6610

Max Act: 2.0028. Min Act: -0.0001

Data Index: 1252167 (C4 (Web Text))

Max Activating Token Index: 583

Text #11

Max Range: 3.6610. Min Range: -3.6610

Max Act: 1.7739. Min Act: -0.0001

Data Index: 827106 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 3.6610. Min Range: -3.6610

Max Act: 1.8833. Min Act: -0.0001

Data Index: 1021276 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 3.6610. Min Range: -3.6610

Max Act: 1.9808. Min Act: -0.0001

Data Index: 1269577 (C4 (Web Text))

Max Activating Token Index: 508

Text #14

Max Range: 3.6610. Min Range: -3.6610

Max Act: 1.7682. Min Act: -0.0001

Data Index: 1088026 (C4 (Web Text))

Max Activating Token Index: 331

Text #15

Max Range: 3.6610. Min Range: -3.6610

Max Act: 1.9553. Min Act: -0.0001

Data Index: 144943 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 3.6610. Min Range: -3.6610

Max Act: 1.9804. Min Act: -0.0001

Data Index: 1227512 (C4 (Web Text))

Max Activating Token Index: 610

Text #17

Max Range: 3.6610. Min Range: -3.6610

Max Act: 1.7826. Min Act: -0.0001

Data Index: 444955 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 3.6610. Min Range: -3.6610

Max Act: 1.9212. Min Act: -0.0001

Data Index: 305734 (C4 (Web Text))

Max Activating Token Index: 85

Text #19

Max Range: 3.6610. Min Range: -3.6610

Max Act: 1.7837. Min Act: -0.0001

Data Index: 784927 (C4 (Web Text))

Max Activating Token Index: 264