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

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

Neuron 632 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: 0.4559. Min Range: -0.4559

Max Act: 0.4559. Min Act: -0.0001

Data Index: 1583629 (Python Code)

Max Activating Token Index: 874

Text #1

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.4205. Min Act: -0.0001

Data Index: 1424221 (Python Code)

Max Activating Token Index: 670

Text #2

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.4457. Min Act: -0.0001

Data Index: 45228 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.4035. Min Act: -0.0001

Data Index: 1189489 (C4 (Web Text))

Max Activating Token Index: 505

Text #4

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.4027. Min Act: -0.0001

Data Index: 1575447 (Python Code)

Max Activating Token Index: 214

Text #5

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.4258. Min Act: -0.0000

Data Index: 936276 (C4 (Web Text))

Max Activating Token Index: 350

Text #6

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.3839. Min Act: -0.0000

Data Index: 1082458 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.3677. Min Act: -0.0000

Data Index: 602131 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.3947. Min Act: -0.0000

Data Index: 510273 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.3327. Min Act: -0.0000

Data Index: 1595125 (Python Code)

Max Activating Token Index: 784

Text #10

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.3815. Min Act: -0.0001

Data Index: 1564405 (Python Code)

Max Activating Token Index: 895

Text #11

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.3712. Min Act: -0.0001

Data Index: 1468968 (Python Code)

Max Activating Token Index: 652

Text #12

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.3389. Min Act: -0.0000

Data Index: 1190129 (C4 (Web Text))

Max Activating Token Index: 1012

Text #13

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.3433. Min Act: -0.0000

Data Index: 423819 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.3441. Min Act: -0.0001

Data Index: 1247185 (C4 (Web Text))

Max Activating Token Index: 899

Text #15

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.3588. Min Act: -0.0000

Data Index: 456316 (C4 (Web Text))

Max Activating Token Index: 752

Text #16

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.3314. Min Act: -0.0001

Data Index: 570257 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.3343. Min Act: -0.0000

Data Index: 1406153 (Python Code)

Max Activating Token Index: 328

Text #18

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.3443. Min Act: -0.0000

Data Index: 1468921 (Python Code)

Max Activating Token Index: 972

Text #19

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.3423. Min Act: -0.0000

Data Index: 614579 (C4 (Web Text))

Max Activating Token Index: 228