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

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

Neuron 302 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6578. Min Range: -2.6578

Max Act: 2.6578. Min Act: -0.0000

Data Index: 641577 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 2.6578. Min Range: -2.6578

Max Act: 2.2695. Min Act: -0.0000

Data Index: 883462 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 2.6578. Min Range: -2.6578

Max Act: 2.2509. Min Act: -0.0000

Data Index: 1624206 (Python Code)

Max Activating Token Index: 393

Text #3

Max Range: 2.6578. Min Range: -2.6578

Max Act: 2.1933. Min Act: -0.0000

Data Index: 56072 (C4 (Web Text))

Max Activating Token Index: 480

Text #4

Max Range: 2.6578. Min Range: -2.6578

Max Act: 2.1308. Min Act: -0.0000

Data Index: 1652049 (Python Code)

Max Activating Token Index: 248

Text #5

Max Range: 2.6578. Min Range: -2.6578

Max Act: 1.9526. Min Act: -0.0000

Data Index: 1487449 (Python Code)

Max Activating Token Index: 861

Text #6

Max Range: 2.6578. Min Range: -2.6578

Max Act: 2.0500. Min Act: -0.0000

Data Index: 613494 (C4 (Web Text))

Max Activating Token Index: 1002

Text #7

Max Range: 2.6578. Min Range: -2.6578

Max Act: 2.1254. Min Act: -0.0000

Data Index: 1395518 (Python Code)

Max Activating Token Index: 705

Text #8

Max Range: 2.6578. Min Range: -2.6578

Max Act: 2.1171. Min Act: -0.0000

Data Index: 633797 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 2.6578. Min Range: -2.6578

Max Act: 1.8286. Min Act: -0.0000

Data Index: 1018041 (C4 (Web Text))

Max Activating Token Index: 298

Text #10

Max Range: 2.6578. Min Range: -2.6578

Max Act: 1.9949. Min Act: -0.0000

Data Index: 134782 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 2.6578. Min Range: -2.6578

Max Act: 1.9803. Min Act: -0.0000

Data Index: 1296308 (C4 (Web Text))

Max Activating Token Index: 866

Text #12

Max Range: 2.6578. Min Range: -2.6578

Max Act: 1.8641. Min Act: -0.0000

Data Index: 266288 (C4 (Web Text))

Max Activating Token Index: 712

Text #13

Max Range: 2.6578. Min Range: -2.6578

Max Act: 1.7951. Min Act: -0.0000

Data Index: 1489400 (Python Code)

Max Activating Token Index: 341

Text #14

Max Range: 2.6578. Min Range: -2.6578

Max Act: 1.7232. Min Act: -0.0000

Data Index: 1515583 (Python Code)

Max Activating Token Index: 744

Text #15

Max Range: 2.6578. Min Range: -2.6578

Max Act: 1.8162. Min Act: -0.0000

Data Index: 691450 (C4 (Web Text))

Max Activating Token Index: 231

Text #16

Max Range: 2.6578. Min Range: -2.6578

Max Act: 1.7633. Min Act: -0.0000

Data Index: 1570407 (Python Code)

Max Activating Token Index: 293

Text #17

Max Range: 2.6578. Min Range: -2.6578

Max Act: 1.6615. Min Act: -0.0000

Data Index: 346151 (C4 (Web Text))

Max Activating Token Index: 953

Text #18

Max Range: 2.6578. Min Range: -2.6578

Max Act: 1.7419. Min Act: -0.0000

Data Index: 55904 (C4 (Web Text))

Max Activating Token Index: 336

Text #19

Max Range: 2.6578. Min Range: -2.6578

Max Act: 1.4935. Min Act: -0.0000

Data Index: 766496 (C4 (Web Text))

Max Activating Token Index: 379