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

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

Neuron 3856 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0728. Min Range: -3.0728

Max Act: 3.0728. Min Act: -0.0000

Data Index: 1242530 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 3.0728. Min Range: -3.0728

Max Act: 2.9117. Min Act: -0.0000

Data Index: 8621 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 3.0728. Min Range: -3.0728

Max Act: 2.6356. Min Act: -0.0000

Data Index: 1066087 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 3.0728. Min Range: -3.0728

Max Act: 2.8850. Min Act: -0.0000

Data Index: 330327 (C4 (Web Text))

Max Activating Token Index: 244

Text #4

Max Range: 3.0728. Min Range: -3.0728

Max Act: 2.4575. Min Act: -0.0000

Data Index: 939736 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 3.0728. Min Range: -3.0728

Max Act: 2.4970. Min Act: -0.0000

Data Index: 1206779 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 3.0728. Min Range: -3.0728

Max Act: 2.6196. Min Act: -0.0001

Data Index: 456092 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 3.0728. Min Range: -3.0728

Max Act: 2.4429. Min Act: -0.0001

Data Index: 1125904 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 3.0728. Min Range: -3.0728

Max Act: 2.7209. Min Act: -0.0000

Data Index: 461372 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 3.0728. Min Range: -3.0728

Max Act: 2.5268. Min Act: -0.0001

Data Index: 1654080 (Python Code)

Max Activating Token Index: 287

Text #10

Max Range: 3.0728. Min Range: -3.0728

Max Act: 2.4880. Min Act: -0.0000

Data Index: 1317640 (C4 (Web Text))

Max Activating Token Index: 84

Text #11

Max Range: 3.0728. Min Range: -3.0728

Max Act: 2.6082. Min Act: -0.0000

Data Index: 891519 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 3.0728. Min Range: -3.0728

Max Act: 2.6886. Min Act: -0.0000

Data Index: 1151379 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 3.0728. Min Range: -3.0728

Max Act: 2.3273. Min Act: -0.0000

Data Index: 628330 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 3.0728. Min Range: -3.0728

Max Act: 2.5982. Min Act: -0.0000

Data Index: 1488593 (Python Code)

Max Activating Token Index: 605

Text #15

Max Range: 3.0728. Min Range: -3.0728

Max Act: 2.4426. Min Act: -0.0000

Data Index: 790159 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 3.0728. Min Range: -3.0728

Max Act: 2.4293. Min Act: -0.0000

Data Index: 362205 (C4 (Web Text))

Max Activating Token Index: 629

Text #17

Max Range: 3.0728. Min Range: -3.0728

Max Act: 2.1583. Min Act: -0.0000

Data Index: 277161 (C4 (Web Text))

Max Activating Token Index: 192

Text #18

Max Range: 3.0728. Min Range: -3.0728

Max Act: 2.3952. Min Act: -0.0000

Data Index: 1104788 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 3.0728. Min Range: -3.0728

Max Act: 2.1426. Min Act: -0.0000

Data Index: 1647098 (Python Code)

Max Activating Token Index: 524