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

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

Neuron 1514 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4771. Min Range: -4.4771

Max Act: 4.4675. Min Act: -0.0000

Data Index: 1201670 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 4.4771. Min Range: -4.4771

Max Act: 4.1356. Min Act: -0.0000

Data Index: 664090 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 4.4771. Min Range: -4.4771

Max Act: 4.3408. Min Act: -0.0000

Data Index: 1267046 (C4 (Web Text))

Max Activating Token Index: 414

Text #3

Max Range: 4.4771. Min Range: -4.4771

Max Act: 4.4771. Min Act: -0.0000

Data Index: 610435 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 4.4771. Min Range: -4.4771

Max Act: 4.0894. Min Act: -0.0000

Data Index: 504494 (C4 (Web Text))

Max Activating Token Index: 779

Text #5

Max Range: 4.4771. Min Range: -4.4771

Max Act: 4.0655. Min Act: -0.0000

Data Index: 792122 (C4 (Web Text))

Max Activating Token Index: 641

Text #6

Max Range: 4.4771. Min Range: -4.4771

Max Act: 3.7853. Min Act: -0.0000

Data Index: 920086 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 4.4771. Min Range: -4.4771

Max Act: 3.6967. Min Act: -0.0000

Data Index: 1305373 (C4 (Web Text))

Max Activating Token Index: 988

Text #8

Max Range: 4.4771. Min Range: -4.4771

Max Act: 3.3197. Min Act: -0.0000

Data Index: 22111 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 4.4771. Min Range: -4.4771

Max Act: 3.7571. Min Act: -0.0000

Data Index: 931691 (C4 (Web Text))

Max Activating Token Index: 303

Text #10

Max Range: 4.4771. Min Range: -4.4771

Max Act: 3.4075. Min Act: -0.0000

Data Index: 602006 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 4.4771. Min Range: -4.4771

Max Act: 3.4164. Min Act: -0.0000

Data Index: 5493 (C4 (Web Text))

Max Activating Token Index: 367

Text #12

Max Range: 4.4771. Min Range: -4.4771

Max Act: 3.4017. Min Act: -0.0000

Data Index: 823399 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 4.4771. Min Range: -4.4771

Max Act: 3.2929. Min Act: -0.0000

Data Index: 934212 (C4 (Web Text))

Max Activating Token Index: 708

Text #14

Max Range: 4.4771. Min Range: -4.4771

Max Act: 3.3116. Min Act: -0.0000

Data Index: 646104 (C4 (Web Text))

Max Activating Token Index: 646

Text #15

Max Range: 4.4771. Min Range: -4.4771

Max Act: 3.2289. Min Act: -0.0000

Data Index: 1291807 (C4 (Web Text))

Max Activating Token Index: 299

Text #16

Max Range: 4.4771. Min Range: -4.4771

Max Act: 3.6431. Min Act: -0.0000

Data Index: 596773 (C4 (Web Text))

Max Activating Token Index: 454

Text #17

Max Range: 4.4771. Min Range: -4.4771

Max Act: 3.4537. Min Act: -0.0000

Data Index: 2998 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 4.4771. Min Range: -4.4771

Max Act: 3.9788. Min Act: -0.0000

Data Index: 163862 (C4 (Web Text))

Max Activating Token Index: 628

Text #19

Max Range: 4.4771. Min Range: -4.4771

Max Act: 3.4566. Min Act: -0.0000

Data Index: 803821 (C4 (Web Text))

Max Activating Token Index: 320