Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2608 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6174. Min Range: -1.6174

Max Act: 1.6174. Min Act: -0.0000

Data Index: 412848 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 1.6174. Min Range: -1.6174

Max Act: 1.3873. Min Act: -0.0000

Data Index: 1196584 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 1.6174. Min Range: -1.6174

Max Act: 1.3334. Min Act: -0.0000

Data Index: 841374 (C4 (Web Text))

Max Activating Token Index: 845

Text #3

Max Range: 1.6174. Min Range: -1.6174

Max Act: 1.1982. Min Act: -0.0001

Data Index: 1104379 (C4 (Web Text))

Max Activating Token Index: 68

Text #4

Max Range: 1.6174. Min Range: -1.6174

Max Act: 1.3630. Min Act: -0.0001

Data Index: 451139 (C4 (Web Text))

Max Activating Token Index: 890

Text #5

Max Range: 1.6174. Min Range: -1.6174

Max Act: 1.3776. Min Act: -0.0000

Data Index: 783267 (C4 (Web Text))

Max Activating Token Index: 669

Text #6

Max Range: 1.6174. Min Range: -1.6174

Max Act: 1.2161. Min Act: -0.0000

Data Index: 707901 (C4 (Web Text))

Max Activating Token Index: 219

Text #7

Max Range: 1.6174. Min Range: -1.6174

Max Act: 1.1718. Min Act: -0.0001

Data Index: 918862 (C4 (Web Text))

Max Activating Token Index: 431

Text #8

Max Range: 1.6174. Min Range: -1.6174

Max Act: 1.0629. Min Act: -0.0000

Data Index: 411244 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 1.6174. Min Range: -1.6174

Max Act: 1.1938. Min Act: -0.0000

Data Index: 1193913 (C4 (Web Text))

Max Activating Token Index: 415

Text #10

Max Range: 1.6174. Min Range: -1.6174

Max Act: 1.1182. Min Act: -0.0000

Data Index: 1067978 (C4 (Web Text))

Max Activating Token Index: 736

Text #11

Max Range: 1.6174. Min Range: -1.6174

Max Act: 1.0214. Min Act: -0.0000

Data Index: 535126 (C4 (Web Text))

Max Activating Token Index: 994

Text #12

Max Range: 1.6174. Min Range: -1.6174

Max Act: 1.0940. Min Act: -0.0000

Data Index: 381814 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 1.6174. Min Range: -1.6174

Max Act: 1.0588. Min Act: -0.0001

Data Index: 1297157 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 1.6174. Min Range: -1.6174

Max Act: 1.0562. Min Act: -0.0001

Data Index: 282835 (C4 (Web Text))

Max Activating Token Index: 874

Text #15

Max Range: 1.6174. Min Range: -1.6174

Max Act: 1.0812. Min Act: -0.0000

Data Index: 972201 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 1.6174. Min Range: -1.6174

Max Act: 1.0422. Min Act: -0.0001

Data Index: 910958 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 1.6174. Min Range: -1.6174

Max Act: 0.8936. Min Act: -0.0001

Data Index: 878261 (C4 (Web Text))

Max Activating Token Index: 606

Text #18

Max Range: 1.6174. Min Range: -1.6174

Max Act: 0.9491. Min Act: -0.0000

Data Index: 1032877 (C4 (Web Text))

Max Activating Token Index: 679

Text #19

Max Range: 1.6174. Min Range: -1.6174

Max Act: 0.9165. Min Act: -0.0001

Data Index: 580303 (C4 (Web Text))

Max Activating Token Index: 958