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

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

Neuron 3492 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.8212. Min Act: -0.0000

Data Index: 89859 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.5747. Min Act: 0.0000

Data Index: 982791 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.5418. Min Act: 0.0000

Data Index: 1287164 (C4 (Web Text))

Max Activating Token Index: 934

Text #3

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.5280. Min Act: -0.0000

Data Index: 470995 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.4807. Min Act: -0.0000

Data Index: 1056410 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.4814. Min Act: -0.0000

Data Index: 662240 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.5190. Min Act: -0.0000

Data Index: 868064 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.4867. Min Act: -0.0000

Data Index: 637463 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.4964. Min Act: -0.0000

Data Index: 914791 (C4 (Web Text))

Max Activating Token Index: 571

Text #9

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.4735. Min Act: 0.0001

Data Index: 89826 (C4 (Web Text))

Max Activating Token Index: 949

Text #10

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.4616. Min Act: -0.0000

Data Index: 1032349 (C4 (Web Text))

Max Activating Token Index: 513

Text #11

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.5066. Min Act: -0.0000

Data Index: 392974 (C4 (Web Text))

Max Activating Token Index: 834

Text #12

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.4701. Min Act: -0.0000

Data Index: 1276766 (C4 (Web Text))

Max Activating Token Index: 983

Text #13

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.4706. Min Act: -0.0000

Data Index: 617231 (C4 (Web Text))

Max Activating Token Index: 717

Text #14

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.4726. Min Act: -0.0000

Data Index: 337115 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.4175. Min Act: -0.0000

Data Index: 1015430 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.4442. Min Act: -0.0000

Data Index: 188075 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.4205. Min Act: -0.0000

Data Index: 992650 (C4 (Web Text))

Max Activating Token Index: 429

Text #18

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.4571. Min Act: -0.0000

Data Index: 916689 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.4370. Min Act: -0.0000

Data Index: 480127 (C4 (Web Text))

Max Activating Token Index: 944