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

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

Neuron 367 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0871. Min Range: -2.0871

Max Act: 2.0871. Min Act: -0.0000

Data Index: 17310 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 2.0871. Min Range: -2.0871

Max Act: 1.9680. Min Act: -0.0000

Data Index: 331433 (C4 (Web Text))

Max Activating Token Index: 663

Text #2

Max Range: 2.0871. Min Range: -2.0871

Max Act: 2.0273. Min Act: -0.0000

Data Index: 277647 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 2.0871. Min Range: -2.0871

Max Act: 1.8983. Min Act: -0.0000

Data Index: 415661 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 2.0871. Min Range: -2.0871

Max Act: 1.7985. Min Act: -0.0000

Data Index: 654107 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 2.0871. Min Range: -2.0871

Max Act: 1.7880. Min Act: -0.0000

Data Index: 609578 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 2.0871. Min Range: -2.0871

Max Act: 1.6928. Min Act: -0.0000

Data Index: 252483 (C4 (Web Text))

Max Activating Token Index: 796

Text #7

Max Range: 2.0871. Min Range: -2.0871

Max Act: 1.6845. Min Act: -0.0000

Data Index: 52524 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 2.0871. Min Range: -2.0871

Max Act: 1.6525. Min Act: -0.0000

Data Index: 76347 (C4 (Web Text))

Max Activating Token Index: 808

Text #9

Max Range: 2.0871. Min Range: -2.0871

Max Act: 1.6450. Min Act: -0.0000

Data Index: 520161 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 2.0871. Min Range: -2.0871

Max Act: 1.6306. Min Act: -0.0000

Data Index: 1098629 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 2.0871. Min Range: -2.0871

Max Act: 1.5307. Min Act: -0.0000

Data Index: 526600 (C4 (Web Text))

Max Activating Token Index: 390

Text #12

Max Range: 2.0871. Min Range: -2.0871

Max Act: 1.6194. Min Act: -0.0000

Data Index: 123384 (C4 (Web Text))

Max Activating Token Index: 949

Text #13

Max Range: 2.0871. Min Range: -2.0871

Max Act: 1.6082. Min Act: -0.0000

Data Index: 953609 (C4 (Web Text))

Max Activating Token Index: 134

Text #14

Max Range: 2.0871. Min Range: -2.0871

Max Act: 1.6007. Min Act: -0.0000

Data Index: 848715 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 2.0871. Min Range: -2.0871

Max Act: 1.5024. Min Act: -0.0000

Data Index: 244348 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 2.0871. Min Range: -2.0871

Max Act: 1.6812. Min Act: -0.0000

Data Index: 1501922 (Python Code)

Max Activating Token Index: 989

Text #17

Max Range: 2.0871. Min Range: -2.0871

Max Act: 1.5834. Min Act: -0.0000

Data Index: 745317 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 2.0871. Min Range: -2.0871

Max Act: 1.4614. Min Act: -0.0000

Data Index: 439249 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 2.0871. Min Range: -2.0871

Max Act: 1.5483. Min Act: -0.0000

Data Index: 692026 (C4 (Web Text))

Max Activating Token Index: 658