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

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

Neuron 1479 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3777. Min Range: -1.3777

Max Act: 1.3777. Min Act: -0.0000

Data Index: 1467724 (Python Code)

Max Activating Token Index: 334

Text #1

Max Range: 1.3777. Min Range: -1.3777

Max Act: 1.3001. Min Act: -0.0000

Data Index: 1436397 (Python Code)

Max Activating Token Index: 63

Text #2

Max Range: 1.3777. Min Range: -1.3777

Max Act: 1.1597. Min Act: -0.0000

Data Index: 1546152 (Python Code)

Max Activating Token Index: 786

Text #3

Max Range: 1.3777. Min Range: -1.3777

Max Act: 1.1321. Min Act: -0.0000

Data Index: 1381372 (Python Code)

Max Activating Token Index: 479

Text #4

Max Range: 1.3777. Min Range: -1.3777

Max Act: 1.1038. Min Act: -0.0000

Data Index: 692224 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 1.3777. Min Range: -1.3777

Max Act: 1.1098. Min Act: -0.0000

Data Index: 732879 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 1.3777. Min Range: -1.3777

Max Act: 1.0917. Min Act: -0.0000

Data Index: 1449193 (Python Code)

Max Activating Token Index: 273

Text #7

Max Range: 1.3777. Min Range: -1.3777

Max Act: 1.0206. Min Act: -0.0000

Data Index: 1541252 (Python Code)

Max Activating Token Index: 947

Text #8

Max Range: 1.3777. Min Range: -1.3777

Max Act: 1.0599. Min Act: -0.0000

Data Index: 1416249 (Python Code)

Max Activating Token Index: 372

Text #9

Max Range: 1.3777. Min Range: -1.3777

Max Act: 1.0218. Min Act: -0.0000

Data Index: 140573 (C4 (Web Text))

Max Activating Token Index: 977

Text #10

Max Range: 1.3777. Min Range: -1.3777

Max Act: 1.0563. Min Act: -0.0000

Data Index: 390820 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 1.3777. Min Range: -1.3777

Max Act: 1.0047. Min Act: -0.0000

Data Index: 67633 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 1.3777. Min Range: -1.3777

Max Act: 1.0324. Min Act: -0.0000

Data Index: 1362211 (Python Code)

Max Activating Token Index: 303

Text #13

Max Range: 1.3777. Min Range: -1.3777

Max Act: 0.9952. Min Act: -0.0000

Data Index: 1053885 (C4 (Web Text))

Max Activating Token Index: 233

Text #14

Max Range: 1.3777. Min Range: -1.3777

Max Act: 0.9967. Min Act: -0.0000

Data Index: 789952 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 1.3777. Min Range: -1.3777

Max Act: 0.9699. Min Act: -0.0000

Data Index: 547813 (C4 (Web Text))

Max Activating Token Index: 248

Text #16

Max Range: 1.3777. Min Range: -1.3777

Max Act: 0.9711. Min Act: -0.0000

Data Index: 1648761 (Python Code)

Max Activating Token Index: 420

Text #17

Max Range: 1.3777. Min Range: -1.3777

Max Act: 0.9937. Min Act: -0.0000

Data Index: 637162 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 1.3777. Min Range: -1.3777

Max Act: 0.9570. Min Act: -0.0000

Data Index: 1018375 (C4 (Web Text))

Max Activating Token Index: 985

Text #19

Max Range: 1.3777. Min Range: -1.3777

Max Act: 0.9432. Min Act: -0.0000

Data Index: 889073 (C4 (Web Text))

Max Activating Token Index: 833