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

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

Neuron 2021 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: 2.5194. Min Range: -2.5194

Max Act: 2.5194. Min Act: -0.0002

Data Index: 1110418 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 2.5194. Min Range: -2.5194

Max Act: 2.3946. Min Act: -0.0002

Data Index: 165064 (C4 (Web Text))

Max Activating Token Index: 408

Text #2

Max Range: 2.5194. Min Range: -2.5194

Max Act: 2.3136. Min Act: -0.0002

Data Index: 180749 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 2.5194. Min Range: -2.5194

Max Act: 2.3575. Min Act: -0.0002

Data Index: 521050 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 2.5194. Min Range: -2.5194

Max Act: 2.2449. Min Act: -0.0002

Data Index: 1078190 (C4 (Web Text))

Max Activating Token Index: 760

Text #5

Max Range: 2.5194. Min Range: -2.5194

Max Act: 2.2893. Min Act: -0.0002

Data Index: 1113416 (C4 (Web Text))

Max Activating Token Index: 3

Text #6

Max Range: 2.5194. Min Range: -2.5194

Max Act: 2.2990. Min Act: -0.0002

Data Index: 1152 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 2.5194. Min Range: -2.5194

Max Act: 2.2434. Min Act: -0.0002

Data Index: 390475 (C4 (Web Text))

Max Activating Token Index: 10

Text #8

Max Range: 2.5194. Min Range: -2.5194

Max Act: 2.1558. Min Act: -0.0003

Data Index: 1013602 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 2.5194. Min Range: -2.5194

Max Act: 2.2104. Min Act: -0.0002

Data Index: 687817 (C4 (Web Text))

Max Activating Token Index: 7

Text #10

Max Range: 2.5194. Min Range: -2.5194

Max Act: 2.2224. Min Act: -0.0002

Data Index: 1217569 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 2.5194. Min Range: -2.5194

Max Act: 2.1659. Min Act: -0.0002

Data Index: 1279562 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 2.5194. Min Range: -2.5194

Max Act: 2.1614. Min Act: -0.0002

Data Index: 162529 (C4 (Web Text))

Max Activating Token Index: 238

Text #13

Max Range: 2.5194. Min Range: -2.5194

Max Act: 2.1724. Min Act: -0.0002

Data Index: 1013884 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 2.5194. Min Range: -2.5194

Max Act: 2.1632. Min Act: -0.0002

Data Index: 421969 (C4 (Web Text))

Max Activating Token Index: 307

Text #15

Max Range: 2.5194. Min Range: -2.5194

Max Act: 2.1802. Min Act: -0.0002

Data Index: 622802 (C4 (Web Text))

Max Activating Token Index: 246

Text #16

Max Range: 2.5194. Min Range: -2.5194

Max Act: 2.2248. Min Act: -0.0002

Data Index: 665792 (C4 (Web Text))

Max Activating Token Index: 7

Text #17

Max Range: 2.5194. Min Range: -2.5194

Max Act: 2.1316. Min Act: -0.0002

Data Index: 306158 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 2.5194. Min Range: -2.5194

Max Act: 2.2537. Min Act: -0.0002

Data Index: 563843 (C4 (Web Text))

Max Activating Token Index: 140

Text #19

Max Range: 2.5194. Min Range: -2.5194

Max Act: 2.2240. Min Act: -0.0002

Data Index: 1236913 (C4 (Web Text))

Max Activating Token Index: 374