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

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

Neuron 127 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3906. Min Range: -3.3906

Max Act: 3.3906. Min Act: -0.0002

Data Index: 794199 (C4 (Web Text))

Max Activating Token Index: 628

Text #1

Max Range: 3.3906. Min Range: -3.3906

Max Act: 2.9724. Min Act: -0.0002

Data Index: 801554 (C4 (Web Text))

Max Activating Token Index: 460

Text #2

Max Range: 3.3906. Min Range: -3.3906

Max Act: 2.6509. Min Act: -0.0002

Data Index: 25117 (C4 (Web Text))

Max Activating Token Index: 468

Text #3

Max Range: 3.3906. Min Range: -3.3906

Max Act: 2.3101. Min Act: -0.0002

Data Index: 814949 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 3.3906. Min Range: -3.3906

Max Act: 2.4975. Min Act: -0.0001

Data Index: 470313 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 3.3906. Min Range: -3.3906

Max Act: 2.5385. Min Act: -0.0001

Data Index: 637134 (C4 (Web Text))

Max Activating Token Index: 140

Text #6

Max Range: 3.3906. Min Range: -3.3906

Max Act: 2.3588. Min Act: -0.0002

Data Index: 758983 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 3.3906. Min Range: -3.3906

Max Act: 2.4837. Min Act: -0.0002

Data Index: 903088 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 3.3906. Min Range: -3.3906

Max Act: 2.3974. Min Act: -0.0002

Data Index: 976033 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 3.3906. Min Range: -3.3906

Max Act: 2.2474. Min Act: -0.0001

Data Index: 946413 (C4 (Web Text))

Max Activating Token Index: 772

Text #10

Max Range: 3.3906. Min Range: -3.3906

Max Act: 2.3037. Min Act: -0.0002

Data Index: 797669 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 3.3906. Min Range: -3.3906

Max Act: 2.2944. Min Act: -0.0001

Data Index: 835898 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 3.3906. Min Range: -3.3906

Max Act: 2.3037. Min Act: -0.0002

Data Index: 832623 (C4 (Web Text))

Max Activating Token Index: 968

Text #13

Max Range: 3.3906. Min Range: -3.3906

Max Act: 2.2943. Min Act: -0.0002

Data Index: 1306535 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 3.3906. Min Range: -3.3906

Max Act: 1.9254. Min Act: -0.0002

Data Index: 912115 (C4 (Web Text))

Max Activating Token Index: 842

Text #15

Max Range: 3.3906. Min Range: -3.3906

Max Act: 2.1185. Min Act: -0.0001

Data Index: 270005 (C4 (Web Text))

Max Activating Token Index: 404

Text #16

Max Range: 3.3906. Min Range: -3.3906

Max Act: 1.9978. Min Act: -0.0002

Data Index: 596193 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 3.3906. Min Range: -3.3906

Max Act: 2.2050. Min Act: -0.0002

Data Index: 579183 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 3.3906. Min Range: -3.3906

Max Act: 1.9831. Min Act: -0.0001

Data Index: 119304 (C4 (Web Text))

Max Activating Token Index: 962

Text #19

Max Range: 3.3906. Min Range: -3.3906

Max Act: 2.0960. Min Act: -0.0002

Data Index: 474733 (C4 (Web Text))

Max Activating Token Index: 517