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

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

Neuron 805 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2452. Min Range: -3.2452

Max Act: 3.2452. Min Act: -0.0000

Data Index: 897248 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 3.2452. Min Range: -3.2452

Max Act: 2.9840. Min Act: -0.0000

Data Index: 407582 (C4 (Web Text))

Max Activating Token Index: 411

Text #2

Max Range: 3.2452. Min Range: -3.2452

Max Act: 3.0164. Min Act: -0.0000

Data Index: 934927 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 3.2452. Min Range: -3.2452

Max Act: 3.0269. Min Act: -0.0000

Data Index: 930368 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 3.2452. Min Range: -3.2452

Max Act: 2.9553. Min Act: -0.0000

Data Index: 246110 (C4 (Web Text))

Max Activating Token Index: 693

Text #5

Max Range: 3.2452. Min Range: -3.2452

Max Act: 2.6418. Min Act: -0.0000

Data Index: 214215 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 3.2452. Min Range: -3.2452

Max Act: 2.5162. Min Act: -0.0000

Data Index: 946714 (C4 (Web Text))

Max Activating Token Index: 883

Text #7

Max Range: 3.2452. Min Range: -3.2452

Max Act: 2.3343. Min Act: -0.0000

Data Index: 790956 (C4 (Web Text))

Max Activating Token Index: 988

Text #8

Max Range: 3.2452. Min Range: -3.2452

Max Act: 2.3068. Min Act: -0.0000

Data Index: 844787 (C4 (Web Text))

Max Activating Token Index: 224

Text #9

Max Range: 3.2452. Min Range: -3.2452

Max Act: 2.4119. Min Act: -0.0000

Data Index: 1351146 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 3.2452. Min Range: -3.2452

Max Act: 2.3630. Min Act: -0.0000

Data Index: 41589 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 3.2452. Min Range: -3.2452

Max Act: 2.3655. Min Act: -0.0000

Data Index: 780104 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 3.2452. Min Range: -3.2452

Max Act: 2.3306. Min Act: -0.0000

Data Index: 94221 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 3.2452. Min Range: -3.2452

Max Act: 2.3227. Min Act: -0.0000

Data Index: 560776 (C4 (Web Text))

Max Activating Token Index: 95

Text #14

Max Range: 3.2452. Min Range: -3.2452

Max Act: 2.2662. Min Act: -0.0000

Data Index: 357476 (C4 (Web Text))

Max Activating Token Index: 1005

Text #15

Max Range: 3.2452. Min Range: -3.2452

Max Act: 2.3818. Min Act: -0.0000

Data Index: 908637 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 3.2452. Min Range: -3.2452

Max Act: 2.1360. Min Act: -0.0000

Data Index: 197787 (C4 (Web Text))

Max Activating Token Index: 246

Text #17

Max Range: 3.2452. Min Range: -3.2452

Max Act: 2.2714. Min Act: -0.0000

Data Index: 1043671 (C4 (Web Text))

Max Activating Token Index: 908

Text #18

Max Range: 3.2452. Min Range: -3.2452

Max Act: 2.3725. Min Act: -0.0000

Data Index: 1125367 (C4 (Web Text))

Max Activating Token Index: 552

Text #19

Max Range: 3.2452. Min Range: -3.2452

Max Act: 2.3528. Min Act: -0.0000

Data Index: 1110817 (C4 (Web Text))

Max Activating Token Index: 654