Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 655 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.4743. Min Act: -0.0000

Data Index: 338215 (C4 (Web Text))

Max Activating Token Index: 925

Text #1

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.4646. Min Act: -0.0000

Data Index: 1006128 (C4 (Web Text))

Max Activating Token Index: 1018

Text #2

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.4579. Min Act: -0.0000

Data Index: 1158335 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.4643. Min Act: -0.0000

Data Index: 352983 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.4116. Min Act: -0.0000

Data Index: 1353300 (C4 (Web Text))

Max Activating Token Index: 614

Text #5

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3885. Min Act: -0.0000

Data Index: 272202 (C4 (Web Text))

Max Activating Token Index: 353

Text #6

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.4026. Min Act: -0.0000

Data Index: 727080 (C4 (Web Text))

Max Activating Token Index: 410

Text #7

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3808. Min Act: -0.0000

Data Index: 149222 (C4 (Web Text))

Max Activating Token Index: 993

Text #8

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3716. Min Act: -0.0000

Data Index: 793504 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3627. Min Act: -0.0000

Data Index: 117118 (C4 (Web Text))

Max Activating Token Index: 938

Text #10

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3684. Min Act: -0.0000

Data Index: 769403 (C4 (Web Text))

Max Activating Token Index: 501

Text #11

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3648. Min Act: -0.0000

Data Index: 777405 (C4 (Web Text))

Max Activating Token Index: 541

Text #12

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3389. Min Act: -0.0000

Data Index: 277683 (C4 (Web Text))

Max Activating Token Index: 648

Text #13

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3594. Min Act: -0.0000

Data Index: 980129 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3470. Min Act: -0.0000

Data Index: 848868 (C4 (Web Text))

Max Activating Token Index: 509

Text #15

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3432. Min Act: -0.0000

Data Index: 186276 (C4 (Web Text))

Max Activating Token Index: 55

Text #16

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3633. Min Act: -0.0000

Data Index: 1246444 (C4 (Web Text))

Max Activating Token Index: 684

Text #17

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3527. Min Act: -0.0000

Data Index: 369712 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3433. Min Act: -0.0000

Data Index: 892240 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 0.4743. Min Range: -0.4743

Max Act: 0.3250. Min Act: -0.0000

Data Index: 93561 (C4 (Web Text))

Max Activating Token Index: 50