Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2724 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3777. Min Range: -1.3777

Max Act: 1.2707. Min Act: -0.0001

Data Index: 596575 (C4 (Web Text))

Max Activating Token Index: 252

Text #1

Max Range: 1.3777. Min Range: -1.3777

Max Act: 1.2165. Min Act: -0.0001

Data Index: 1309102 (C4 (Web Text))

Max Activating Token Index: 889

Text #2

Max Range: 1.3777. Min Range: -1.3777

Max Act: 1.2899. Min Act: -0.0001

Data Index: 263824 (C4 (Web Text))

Max Activating Token Index: 549

Text #3

Max Range: 1.3777. Min Range: -1.3777

Max Act: 1.2672. Min Act: -0.0001

Data Index: 914117 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 1.3777. Min Range: -1.3777

Max Act: 1.2220. Min Act: -0.0001

Data Index: 1211479 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 1.3777. Min Range: -1.3777

Max Act: 1.1237. Min Act: -0.0001

Data Index: 1069336 (C4 (Web Text))

Max Activating Token Index: 99

Text #6

Max Range: 1.3777. Min Range: -1.3777

Max Act: 1.1366. Min Act: -0.0001

Data Index: 1227935 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 1.3777. Min Range: -1.3777

Max Act: 1.0878. Min Act: -0.0001

Data Index: 535244 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 1.3777. Min Range: -1.3777

Max Act: 1.0277. Min Act: -0.0001

Data Index: 971040 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 1.3777. Min Range: -1.3777

Max Act: 1.0030. Min Act: -0.0001

Data Index: 1238173 (C4 (Web Text))

Max Activating Token Index: 150

Text #10

Max Range: 1.3777. Min Range: -1.3777

Max Act: 0.9900. Min Act: -0.0001

Data Index: 1111528 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 1.3777. Min Range: -1.3777

Max Act: 1.3777. Min Act: -0.0001

Data Index: 1233942 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 1.3777. Min Range: -1.3777

Max Act: 1.0066. Min Act: -0.0001

Data Index: 837544 (C4 (Web Text))

Max Activating Token Index: 115

Text #13

Max Range: 1.3777. Min Range: -1.3777

Max Act: 1.0325. Min Act: -0.0001

Data Index: 878641 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 1.3777. Min Range: -1.3777

Max Act: 0.9454. Min Act: -0.0001

Data Index: 16377 (C4 (Web Text))

Max Activating Token Index: 613

Text #15

Max Range: 1.3777. Min Range: -1.3777

Max Act: 0.9053. Min Act: -0.0001

Data Index: 413417 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 1.3777. Min Range: -1.3777

Max Act: 1.0576. Min Act: -0.0001

Data Index: 373970 (C4 (Web Text))

Max Activating Token Index: 152

Text #17

Max Range: 1.3777. Min Range: -1.3777

Max Act: 1.0215. Min Act: -0.0001

Data Index: 616033 (C4 (Web Text))

Max Activating Token Index: 838

Text #18

Max Range: 1.3777. Min Range: -1.3777

Max Act: 0.9233. Min Act: -0.0001

Data Index: 685970 (C4 (Web Text))

Max Activating Token Index: 622

Text #19

Max Range: 1.3777. Min Range: -1.3777

Max Act: 1.0174. Min Act: -0.0001

Data Index: 1094483 (C4 (Web Text))

Max Activating Token Index: 395