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

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

Neuron 1835 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.3930. Min Range: -2.3930

Max Act: 2.3930. Min Act: -0.0002

Data Index: 1192595 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 2.3930. Min Range: -2.3930

Max Act: 2.3110. Min Act: -0.0002

Data Index: 163781 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 2.3930. Min Range: -2.3930

Max Act: 2.2215. Min Act: -0.0001

Data Index: 663200 (C4 (Web Text))

Max Activating Token Index: 500

Text #3

Max Range: 2.3930. Min Range: -2.3930

Max Act: 2.2677. Min Act: -0.0002

Data Index: 119607 (C4 (Web Text))

Max Activating Token Index: 503

Text #4

Max Range: 2.3930. Min Range: -2.3930

Max Act: 2.1780. Min Act: -0.0002

Data Index: 1314142 (C4 (Web Text))

Max Activating Token Index: 408

Text #5

Max Range: 2.3930. Min Range: -2.3930

Max Act: 2.1376. Min Act: -0.0002

Data Index: 959160 (C4 (Web Text))

Max Activating Token Index: 73

Text #6

Max Range: 2.3930. Min Range: -2.3930

Max Act: 2.2430. Min Act: -0.0002

Data Index: 982303 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 2.3930. Min Range: -2.3930

Max Act: 2.2114. Min Act: -0.0002

Data Index: 246707 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 2.3930. Min Range: -2.3930

Max Act: 2.1424. Min Act: -0.0002

Data Index: 248645 (C4 (Web Text))

Max Activating Token Index: 199

Text #9

Max Range: 2.3930. Min Range: -2.3930

Max Act: 2.1100. Min Act: -0.0002

Data Index: 956841 (C4 (Web Text))

Max Activating Token Index: 803

Text #10

Max Range: 2.3930. Min Range: -2.3930

Max Act: 2.1041. Min Act: -0.0002

Data Index: 142040 (C4 (Web Text))

Max Activating Token Index: 887

Text #11

Max Range: 2.3930. Min Range: -2.3930

Max Act: 2.1483. Min Act: -0.0002

Data Index: 438281 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 2.3930. Min Range: -2.3930

Max Act: 2.0756. Min Act: -0.0002

Data Index: 697375 (C4 (Web Text))

Max Activating Token Index: 521

Text #13

Max Range: 2.3930. Min Range: -2.3930

Max Act: 2.1183. Min Act: -0.0002

Data Index: 519519 (C4 (Web Text))

Max Activating Token Index: 481

Text #14

Max Range: 2.3930. Min Range: -2.3930

Max Act: 2.0832. Min Act: -0.0002

Data Index: 172453 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 2.3930. Min Range: -2.3930

Max Act: 2.0902. Min Act: -0.0002

Data Index: 155950 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 2.3930. Min Range: -2.3930

Max Act: 2.1252. Min Act: -0.0001

Data Index: 745188 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 2.3930. Min Range: -2.3930

Max Act: 2.0819. Min Act: -0.0002

Data Index: 837973 (C4 (Web Text))

Max Activating Token Index: 223

Text #18

Max Range: 2.3930. Min Range: -2.3930

Max Act: 2.1481. Min Act: -0.0002

Data Index: 415484 (C4 (Web Text))

Max Activating Token Index: 762

Text #19

Max Range: 2.3930. Min Range: -2.3930

Max Act: 2.0457. Min Act: -0.0002

Data Index: 429445 (C4 (Web Text))

Max Activating Token Index: 110