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

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

Neuron 3082 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7407. Min Range: -2.7407

Max Act: 2.5848. Min Act: -0.0000

Data Index: 101824 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 2.7407. Min Range: -2.7407

Max Act: 2.7407. Min Act: -0.0000

Data Index: 521688 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 2.7407. Min Range: -2.7407

Max Act: 2.1923. Min Act: -0.0000

Data Index: 352079 (C4 (Web Text))

Max Activating Token Index: 971

Text #3

Max Range: 2.7407. Min Range: -2.7407

Max Act: 2.2579. Min Act: -0.0000

Data Index: 213302 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 2.7407. Min Range: -2.7407

Max Act: 2.1265. Min Act: -0.0000

Data Index: 456151 (C4 (Web Text))

Max Activating Token Index: 866

Text #5

Max Range: 2.7407. Min Range: -2.7407

Max Act: 2.0777. Min Act: -0.0000

Data Index: 747316 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 2.7407. Min Range: -2.7407

Max Act: 2.1464. Min Act: -0.0000

Data Index: 10704 (C4 (Web Text))

Max Activating Token Index: 1000

Text #7

Max Range: 2.7407. Min Range: -2.7407

Max Act: 2.0124. Min Act: -0.0000

Data Index: 326429 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 2.7407. Min Range: -2.7407

Max Act: 1.7675. Min Act: -0.0000

Data Index: 40017 (C4 (Web Text))

Max Activating Token Index: 622

Text #9

Max Range: 2.7407. Min Range: -2.7407

Max Act: 1.9483. Min Act: -0.0000

Data Index: 845921 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 2.7407. Min Range: -2.7407

Max Act: 1.9230. Min Act: -0.0000

Data Index: 828331 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 2.7407. Min Range: -2.7407

Max Act: 2.0240. Min Act: -0.0000

Data Index: 187769 (C4 (Web Text))

Max Activating Token Index: 748

Text #12

Max Range: 2.7407. Min Range: -2.7407

Max Act: 1.6964. Min Act: -0.0000

Data Index: 881158 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 2.7407. Min Range: -2.7407

Max Act: 1.7772. Min Act: -0.0000

Data Index: 539038 (C4 (Web Text))

Max Activating Token Index: 406

Text #14

Max Range: 2.7407. Min Range: -2.7407

Max Act: 1.8450. Min Act: -0.0000

Data Index: 476335 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 2.7407. Min Range: -2.7407

Max Act: 1.9482. Min Act: -0.0000

Data Index: 605191 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 2.7407. Min Range: -2.7407

Max Act: 1.7542. Min Act: -0.0000

Data Index: 532608 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 2.7407. Min Range: -2.7407

Max Act: 1.9185. Min Act: -0.0000

Data Index: 1108943 (C4 (Web Text))

Max Activating Token Index: 298

Text #18

Max Range: 2.7407. Min Range: -2.7407

Max Act: 1.7958. Min Act: -0.0000

Data Index: 1311212 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 2.7407. Min Range: -2.7407

Max Act: 1.6964. Min Act: -0.0000

Data Index: 109278 (C4 (Web Text))

Max Activating Token Index: 73