Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3326 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.3401. Min Range: -4.3401

Max Act: 4.3401. Min Act: -0.0000

Data Index: 403421 (C4 (Web Text))

Max Activating Token Index: 265

Text #1

Max Range: 4.3401. Min Range: -4.3401

Max Act: 3.8641. Min Act: -0.0000

Data Index: 706349 (C4 (Web Text))

Max Activating Token Index: 554

Text #2

Max Range: 4.3401. Min Range: -4.3401

Max Act: 3.4835. Min Act: -0.0000

Data Index: 1173959 (C4 (Web Text))

Max Activating Token Index: 165

Text #3

Max Range: 4.3401. Min Range: -4.3401

Max Act: 3.2819. Min Act: -0.0000

Data Index: 1093059 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 4.3401. Min Range: -4.3401

Max Act: 3.3543. Min Act: -0.0000

Data Index: 1388958 (Python Code)

Max Activating Token Index: 421

Text #5

Max Range: 4.3401. Min Range: -4.3401

Max Act: 3.2701. Min Act: -0.0001

Data Index: 1579228 (Python Code)

Max Activating Token Index: 568

Text #6

Max Range: 4.3401. Min Range: -4.3401

Max Act: 3.0625. Min Act: -0.0000

Data Index: 1511093 (Python Code)

Max Activating Token Index: 398

Text #7

Max Range: 4.3401. Min Range: -4.3401

Max Act: 3.0892. Min Act: -0.0000

Data Index: 930353 (C4 (Web Text))

Max Activating Token Index: 876

Text #8

Max Range: 4.3401. Min Range: -4.3401

Max Act: 2.7588. Min Act: -0.0000

Data Index: 671292 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 4.3401. Min Range: -4.3401

Max Act: 2.8993. Min Act: -0.0000

Data Index: 1532918 (Python Code)

Max Activating Token Index: 104

Text #10

Max Range: 4.3401. Min Range: -4.3401

Max Act: 3.0625. Min Act: -0.0000

Data Index: 1408182 (Python Code)

Max Activating Token Index: 242

Text #11

Max Range: 4.3401. Min Range: -4.3401

Max Act: 2.8773. Min Act: -0.0000

Data Index: 705110 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 4.3401. Min Range: -4.3401

Max Act: 2.8692. Min Act: -0.0000

Data Index: 893403 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 4.3401. Min Range: -4.3401

Max Act: 2.8606. Min Act: -0.0000

Data Index: 26403 (C4 (Web Text))

Max Activating Token Index: 905

Text #14

Max Range: 4.3401. Min Range: -4.3401

Max Act: 2.9692. Min Act: -0.0000

Data Index: 1497927 (Python Code)

Max Activating Token Index: 725

Text #15

Max Range: 4.3401. Min Range: -4.3401

Max Act: 2.8065. Min Act: -0.0000

Data Index: 55884 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 4.3401. Min Range: -4.3401

Max Act: 2.8028. Min Act: -0.0000

Data Index: 1648532 (Python Code)

Max Activating Token Index: 274

Text #17

Max Range: 4.3401. Min Range: -4.3401

Max Act: 2.7200. Min Act: -0.0000

Data Index: 250363 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 4.3401. Min Range: -4.3401

Max Act: 2.5887. Min Act: -0.0001

Data Index: 1449165 (Python Code)

Max Activating Token Index: 290

Text #19

Max Range: 4.3401. Min Range: -4.3401

Max Act: 2.5985. Min Act: -0.0000

Data Index: 605898 (C4 (Web Text))

Max Activating Token Index: 840