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

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

Neuron 3212 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0934. Min Range: -2.0934

Max Act: 2.0934. Min Act: -0.0000

Data Index: 964242 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 2.0934. Min Range: -2.0934

Max Act: 2.0002. Min Act: -0.0000

Data Index: 1183138 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 2.0934. Min Range: -2.0934

Max Act: 1.9858. Min Act: -0.0000

Data Index: 609076 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 2.0934. Min Range: -2.0934

Max Act: 1.7752. Min Act: -0.0000

Data Index: 793249 (C4 (Web Text))

Max Activating Token Index: 500

Text #4

Max Range: 2.0934. Min Range: -2.0934

Max Act: 1.6371. Min Act: -0.0000

Data Index: 1101698 (C4 (Web Text))

Max Activating Token Index: 420

Text #5

Max Range: 2.0934. Min Range: -2.0934

Max Act: 1.4894. Min Act: -0.0000

Data Index: 678982 (C4 (Web Text))

Max Activating Token Index: 497

Text #6

Max Range: 2.0934. Min Range: -2.0934

Max Act: 1.5678. Min Act: -0.0000

Data Index: 96822 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 2.0934. Min Range: -2.0934

Max Act: 1.4579. Min Act: -0.0000

Data Index: 688040 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 2.0934. Min Range: -2.0934

Max Act: 1.5273. Min Act: -0.0000

Data Index: 1317705 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 2.0934. Min Range: -2.0934

Max Act: 1.4207. Min Act: -0.0000

Data Index: 1170532 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 2.0934. Min Range: -2.0934

Max Act: 1.5160. Min Act: -0.0000

Data Index: 962652 (C4 (Web Text))

Max Activating Token Index: 771

Text #11

Max Range: 2.0934. Min Range: -2.0934

Max Act: 1.4609. Min Act: -0.0000

Data Index: 1305874 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 2.0934. Min Range: -2.0934

Max Act: 1.4554. Min Act: -0.0000

Data Index: 990412 (C4 (Web Text))

Max Activating Token Index: 843

Text #13

Max Range: 2.0934. Min Range: -2.0934

Max Act: 1.4057. Min Act: -0.0000

Data Index: 597067 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 2.0934. Min Range: -2.0934

Max Act: 1.4543. Min Act: -0.0000

Data Index: 984939 (C4 (Web Text))

Max Activating Token Index: 305

Text #15

Max Range: 2.0934. Min Range: -2.0934

Max Act: 1.3789. Min Act: -0.0000

Data Index: 895276 (C4 (Web Text))

Max Activating Token Index: 115

Text #16

Max Range: 2.0934. Min Range: -2.0934

Max Act: 1.2244. Min Act: -0.0000

Data Index: 108631 (C4 (Web Text))

Max Activating Token Index: 903

Text #17

Max Range: 2.0934. Min Range: -2.0934

Max Act: 1.2770. Min Act: -0.0000

Data Index: 1045720 (C4 (Web Text))

Max Activating Token Index: 514

Text #18

Max Range: 2.0934. Min Range: -2.0934

Max Act: 1.4975. Min Act: -0.0000

Data Index: 334231 (C4 (Web Text))

Max Activating Token Index: 828

Text #19

Max Range: 2.0934. Min Range: -2.0934

Max Act: 1.3369. Min Act: -0.0000

Data Index: 430948 (C4 (Web Text))

Max Activating Token Index: 115