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

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

Neuron 5074 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0416. Min Range: -3.0416

Max Act: 3.0416. Min Act: -0.0000

Data Index: 388220 (C4 (Web Text))

Max Activating Token Index: 502

Text #1

Max Range: 3.0416. Min Range: -3.0416

Max Act: 2.6735. Min Act: -0.0000

Data Index: 439784 (C4 (Web Text))

Max Activating Token Index: 788

Text #2

Max Range: 3.0416. Min Range: -3.0416

Max Act: 2.6636. Min Act: -0.0000

Data Index: 1214954 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 3.0416. Min Range: -3.0416

Max Act: 2.6144. Min Act: -0.0000

Data Index: 1178670 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 3.0416. Min Range: -3.0416

Max Act: 2.5886. Min Act: -0.0000

Data Index: 341930 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 3.0416. Min Range: -3.0416

Max Act: 2.5411. Min Act: -0.0000

Data Index: 133253 (C4 (Web Text))

Max Activating Token Index: 725

Text #6

Max Range: 3.0416. Min Range: -3.0416

Max Act: 2.9269. Min Act: -0.0000

Data Index: 35536 (C4 (Web Text))

Max Activating Token Index: 287

Text #7

Max Range: 3.0416. Min Range: -3.0416

Max Act: 2.5744. Min Act: -0.0000

Data Index: 296263 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 3.0416. Min Range: -3.0416

Max Act: 2.5164. Min Act: -0.0000

Data Index: 185790 (C4 (Web Text))

Max Activating Token Index: 533

Text #9

Max Range: 3.0416. Min Range: -3.0416

Max Act: 2.5098. Min Act: -0.0000

Data Index: 577014 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 3.0416. Min Range: -3.0416

Max Act: 2.3523. Min Act: -0.0000

Data Index: 951532 (C4 (Web Text))

Max Activating Token Index: 140

Text #11

Max Range: 3.0416. Min Range: -3.0416

Max Act: 2.3304. Min Act: -0.0000

Data Index: 1127697 (C4 (Web Text))

Max Activating Token Index: 678

Text #12

Max Range: 3.0416. Min Range: -3.0416

Max Act: 2.4429. Min Act: -0.0000

Data Index: 118548 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 3.0416. Min Range: -3.0416

Max Act: 2.5637. Min Act: -0.0000

Data Index: 136117 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 3.0416. Min Range: -3.0416

Max Act: 2.4238. Min Act: -0.0000

Data Index: 480773 (C4 (Web Text))

Max Activating Token Index: 451

Text #15

Max Range: 3.0416. Min Range: -3.0416

Max Act: 2.1713. Min Act: -0.0000

Data Index: 585018 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 3.0416. Min Range: -3.0416

Max Act: 2.5130. Min Act: -0.0000

Data Index: 705078 (C4 (Web Text))

Max Activating Token Index: 842

Text #17

Max Range: 3.0416. Min Range: -3.0416

Max Act: 2.4061. Min Act: -0.0000

Data Index: 983923 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 3.0416. Min Range: -3.0416

Max Act: 2.2811. Min Act: -0.0000

Data Index: 272744 (C4 (Web Text))

Max Activating Token Index: 340

Text #19

Max Range: 3.0416. Min Range: -3.0416

Max Act: 2.2840. Min Act: -0.0000

Data Index: 160392 (C4 (Web Text))

Max Activating Token Index: 958