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

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

Neuron 1650 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.3379. Min Act: -0.0000

Data Index: 176440 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.3893. Min Act: -0.0000

Data Index: 536126 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.1907. Min Act: -0.0000

Data Index: 178436 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.1638. Min Act: -0.0000

Data Index: 1086041 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.1502. Min Act: -0.0000

Data Index: 469671 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.1308. Min Act: -0.0000

Data Index: 983628 (C4 (Web Text))

Max Activating Token Index: 99

Text #6

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.1114. Min Act: -0.0000

Data Index: 1274021 (C4 (Web Text))

Max Activating Token Index: 198

Text #7

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.0327. Min Act: -0.0000

Data Index: 1455914 (Python Code)

Max Activating Token Index: 454

Text #8

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.0920. Min Act: -0.0000

Data Index: 1141254 (C4 (Web Text))

Max Activating Token Index: 99

Text #9

Max Range: 1.3893. Min Range: -1.3893

Max Act: 0.9787. Min Act: -0.0000

Data Index: 71871 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 1.3893. Min Range: -1.3893

Max Act: 0.8295. Min Act: -0.0000

Data Index: 137575 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.0097. Min Act: -0.0000

Data Index: 1543884 (Python Code)

Max Activating Token Index: 425

Text #12

Max Range: 1.3893. Min Range: -1.3893

Max Act: 0.9955. Min Act: -0.0000

Data Index: 972218 (C4 (Web Text))

Max Activating Token Index: 342

Text #13

Max Range: 1.3893. Min Range: -1.3893

Max Act: 1.0058. Min Act: -0.0000

Data Index: 867410 (C4 (Web Text))

Max Activating Token Index: 668

Text #14

Max Range: 1.3893. Min Range: -1.3893

Max Act: 0.9230. Min Act: -0.0000

Data Index: 1089243 (C4 (Web Text))

Max Activating Token Index: 716

Text #15

Max Range: 1.3893. Min Range: -1.3893

Max Act: 0.9396. Min Act: -0.0000

Data Index: 611683 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 1.3893. Min Range: -1.3893

Max Act: 0.9279. Min Act: -0.0000

Data Index: 305944 (C4 (Web Text))

Max Activating Token Index: 451

Text #17

Max Range: 1.3893. Min Range: -1.3893

Max Act: 0.9040. Min Act: -0.0000

Data Index: 416920 (C4 (Web Text))

Max Activating Token Index: 778

Text #18

Max Range: 1.3893. Min Range: -1.3893

Max Act: 0.8665. Min Act: -0.0000

Data Index: 439294 (C4 (Web Text))

Max Activating Token Index: 288

Text #19

Max Range: 1.3893. Min Range: -1.3893

Max Act: 0.9721. Min Act: -0.0000

Data Index: 149748 (C4 (Web Text))

Max Activating Token Index: 69