Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2259 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.4866. Min Act: -0.0003

Data Index: 891704 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.4410. Min Act: -0.0003

Data Index: 338850 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.4683. Min Act: -0.0003

Data Index: 177635 (C4 (Web Text))

Max Activating Token Index: 925

Text #3

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.4353. Min Act: -0.0003

Data Index: 255637 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.4730. Min Act: -0.0003

Data Index: 401786 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.4221. Min Act: -0.0003

Data Index: 610793 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.3838. Min Act: -0.0003

Data Index: 721693 (C4 (Web Text))

Max Activating Token Index: 331

Text #7

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.4306. Min Act: -0.0003

Data Index: 643437 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.4175. Min Act: -0.0003

Data Index: 1279968 (C4 (Web Text))

Max Activating Token Index: 561

Text #9

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.4192. Min Act: -0.0003

Data Index: 480807 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.4212. Min Act: -0.0003

Data Index: 1037340 (C4 (Web Text))

Max Activating Token Index: 944

Text #11

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.4141. Min Act: -0.0003

Data Index: 70891 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.3880. Min Act: -0.0003

Data Index: 256532 (C4 (Web Text))

Max Activating Token Index: 871

Text #13

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.3427. Min Act: -0.0003

Data Index: 518852 (C4 (Web Text))

Max Activating Token Index: 206

Text #14

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.3800. Min Act: -0.0003

Data Index: 88281 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.3723. Min Act: -0.0003

Data Index: 1139499 (C4 (Web Text))

Max Activating Token Index: 844

Text #16

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.3725. Min Act: -0.0003

Data Index: 487322 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.3874. Min Act: -0.0003

Data Index: 993820 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.3682. Min Act: -0.0003

Data Index: 1201714 (C4 (Web Text))

Max Activating Token Index: 128

Text #19

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.3395. Min Act: -0.0003

Data Index: 290817 (C4 (Web Text))

Max Activating Token Index: 186