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

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

Neuron 1407 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7288. Min Range: -3.7288

Max Act: 3.7288. Min Act: -0.0000

Data Index: 825393 (C4 (Web Text))

Max Activating Token Index: 521

Text #1

Max Range: 3.7288. Min Range: -3.7288

Max Act: 3.2863. Min Act: -0.0000

Data Index: 508306 (C4 (Web Text))

Max Activating Token Index: 561

Text #2

Max Range: 3.7288. Min Range: -3.7288

Max Act: 3.0732. Min Act: -0.0000

Data Index: 32142 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 3.7288. Min Range: -3.7288

Max Act: 2.9350. Min Act: -0.0000

Data Index: 1280405 (C4 (Web Text))

Max Activating Token Index: 949

Text #4

Max Range: 3.7288. Min Range: -3.7288

Max Act: 2.7354. Min Act: -0.0000

Data Index: 35466 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 3.7288. Min Range: -3.7288

Max Act: 2.6200. Min Act: -0.0000

Data Index: 579826 (C4 (Web Text))

Max Activating Token Index: 614

Text #6

Max Range: 3.7288. Min Range: -3.7288

Max Act: 2.6322. Min Act: -0.0000

Data Index: 326817 (C4 (Web Text))

Max Activating Token Index: 723

Text #7

Max Range: 3.7288. Min Range: -3.7288

Max Act: 2.4363. Min Act: -0.0000

Data Index: 330362 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 3.7288. Min Range: -3.7288

Max Act: 2.4292. Min Act: -0.0000

Data Index: 1263991 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 3.7288. Min Range: -3.7288

Max Act: 2.2995. Min Act: -0.0000

Data Index: 338381 (C4 (Web Text))

Max Activating Token Index: 663

Text #10

Max Range: 3.7288. Min Range: -3.7288

Max Act: 2.4128. Min Act: -0.0000

Data Index: 907176 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 3.7288. Min Range: -3.7288

Max Act: 2.4969. Min Act: -0.0000

Data Index: 118349 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 3.7288. Min Range: -3.7288

Max Act: 2.2048. Min Act: -0.0000

Data Index: 1068082 (C4 (Web Text))

Max Activating Token Index: 853

Text #13

Max Range: 3.7288. Min Range: -3.7288

Max Act: 2.1936. Min Act: -0.0000

Data Index: 1001452 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 3.7288. Min Range: -3.7288

Max Act: 2.3926. Min Act: -0.0000

Data Index: 1488442 (Python Code)

Max Activating Token Index: 487

Text #15

Max Range: 3.7288. Min Range: -3.7288

Max Act: 2.3313. Min Act: -0.0000

Data Index: 382476 (C4 (Web Text))

Max Activating Token Index: 685

Text #16

Max Range: 3.7288. Min Range: -3.7288

Max Act: 1.9613. Min Act: -0.0000

Data Index: 671639 (C4 (Web Text))

Max Activating Token Index: 901

Text #17

Max Range: 3.7288. Min Range: -3.7288

Max Act: 2.1754. Min Act: -0.0000

Data Index: 1092535 (C4 (Web Text))

Max Activating Token Index: 337

Text #18

Max Range: 3.7288. Min Range: -3.7288

Max Act: 2.0148. Min Act: 0.0000

Data Index: 91262 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 3.7288. Min Range: -3.7288

Max Act: 2.1499. Min Act: -0.0000

Data Index: 1605428 (Python Code)

Max Activating Token Index: 330