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

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

Neuron 1511 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8019. Min Range: -1.8019

Max Act: 1.8019. Min Act: -0.0000

Data Index: 711705 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 1.8019. Min Range: -1.8019

Max Act: 1.5250. Min Act: -0.0000

Data Index: 945047 (C4 (Web Text))

Max Activating Token Index: 322

Text #2

Max Range: 1.8019. Min Range: -1.8019

Max Act: 1.4925. Min Act: -0.0000

Data Index: 543141 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 1.8019. Min Range: -1.8019

Max Act: 1.3706. Min Act: -0.0000

Data Index: 546434 (C4 (Web Text))

Max Activating Token Index: 270

Text #4

Max Range: 1.8019. Min Range: -1.8019

Max Act: 1.3027. Min Act: -0.0000

Data Index: 455412 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 1.8019. Min Range: -1.8019

Max Act: 1.3381. Min Act: -0.0000

Data Index: 836155 (C4 (Web Text))

Max Activating Token Index: 348

Text #6

Max Range: 1.8019. Min Range: -1.8019

Max Act: 1.2918. Min Act: -0.0000

Data Index: 930861 (C4 (Web Text))

Max Activating Token Index: 652

Text #7

Max Range: 1.8019. Min Range: -1.8019

Max Act: 1.3571. Min Act: -0.0000

Data Index: 369720 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 1.8019. Min Range: -1.8019

Max Act: 1.3079. Min Act: -0.0000

Data Index: 299943 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 1.8019. Min Range: -1.8019

Max Act: 1.3268. Min Act: -0.0000

Data Index: 1088319 (C4 (Web Text))

Max Activating Token Index: 938

Text #10

Max Range: 1.8019. Min Range: -1.8019

Max Act: 1.3339. Min Act: -0.0000

Data Index: 784519 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 1.8019. Min Range: -1.8019

Max Act: 1.3219. Min Act: -0.0000

Data Index: 396041 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 1.8019. Min Range: -1.8019

Max Act: 1.2704. Min Act: -0.0000

Data Index: 607590 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 1.8019. Min Range: -1.8019

Max Act: 1.3405. Min Act: -0.0000

Data Index: 195580 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 1.8019. Min Range: -1.8019

Max Act: 1.3188. Min Act: -0.0000

Data Index: 157996 (C4 (Web Text))

Max Activating Token Index: 292

Text #15

Max Range: 1.8019. Min Range: -1.8019

Max Act: 1.2421. Min Act: -0.0000

Data Index: 1322425 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 1.8019. Min Range: -1.8019

Max Act: 1.2820. Min Act: -0.0000

Data Index: 703493 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 1.8019. Min Range: -1.8019

Max Act: 1.1867. Min Act: -0.0000

Data Index: 267572 (C4 (Web Text))

Max Activating Token Index: 415

Text #18

Max Range: 1.8019. Min Range: -1.8019

Max Act: 1.2225. Min Act: -0.0000

Data Index: 161565 (C4 (Web Text))

Max Activating Token Index: 553

Text #19

Max Range: 1.8019. Min Range: -1.8019

Max Act: 1.2088. Min Act: -0.0000

Data Index: 878386 (C4 (Web Text))

Max Activating Token Index: 456