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

Dataset: The Pile

Neuron 1782 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2183. Min Range: -1.2183

Max Act: 1.2183. Min Act: -0.0000

Data Index: 237436 (The Pile)

Max Activating Token Index: 791

Text #1

Max Range: 1.2183. Min Range: -1.2183

Max Act: 1.0725. Min Act: -0.0000

Data Index: 1400244 (The Pile)

Max Activating Token Index: 635

Text #2

Max Range: 1.2183. Min Range: -1.2183

Max Act: 0.9684. Min Act: -0.0000

Data Index: 287334 (The Pile)

Max Activating Token Index: 1020

Text #3

Max Range: 1.2183. Min Range: -1.2183

Max Act: 0.8867. Min Act: -0.0000

Data Index: 869799 (The Pile)

Max Activating Token Index: 505

Text #4

Max Range: 1.2183. Min Range: -1.2183

Max Act: 0.9421. Min Act: -0.0000

Data Index: 855465 (The Pile)

Max Activating Token Index: 693

Text #5

Max Range: 1.2183. Min Range: -1.2183

Max Act: 0.8081. Min Act: -0.0000

Data Index: 670782 (The Pile)

Max Activating Token Index: 510

Text #6

Max Range: 1.2183. Min Range: -1.2183

Max Act: 0.6986. Min Act: -0.0000

Data Index: 446406 (The Pile)

Max Activating Token Index: 546

Text #7

Max Range: 1.2183. Min Range: -1.2183

Max Act: 0.7559. Min Act: -0.0000

Data Index: 1257583 (The Pile)

Max Activating Token Index: 535

Text #8

Max Range: 1.2183. Min Range: -1.2183

Max Act: 0.7141. Min Act: -0.0000

Data Index: 142876 (The Pile)

Max Activating Token Index: 511

Text #9

Max Range: 1.2183. Min Range: -1.2183

Max Act: 0.7340. Min Act: -0.0000

Data Index: 1514107 (The Pile)

Max Activating Token Index: 647

Text #10

Max Range: 1.2183. Min Range: -1.2183

Max Act: 0.6980. Min Act: -0.0000

Data Index: 463473 (The Pile)

Max Activating Token Index: 662

Text #11

Max Range: 1.2183. Min Range: -1.2183

Max Act: 0.7689. Min Act: -0.0000

Data Index: 135289 (The Pile)

Max Activating Token Index: 1015

Text #12

Max Range: 1.2183. Min Range: -1.2183

Max Act: 0.7175. Min Act: -0.0000

Data Index: 253305 (The Pile)

Max Activating Token Index: 349

Text #13

Max Range: 1.2183. Min Range: -1.2183

Max Act: 0.7443. Min Act: -0.0000

Data Index: 1160307 (The Pile)

Max Activating Token Index: 78

Text #14

Max Range: 1.2183. Min Range: -1.2183

Max Act: 0.6864. Min Act: -0.0000

Data Index: 1491401 (The Pile)

Max Activating Token Index: 927

Text #15

Max Range: 1.2183. Min Range: -1.2183

Max Act: 0.6767. Min Act: -0.0000

Data Index: 184750 (The Pile)

Max Activating Token Index: 629

Text #16

Max Range: 1.2183. Min Range: -1.2183

Max Act: 0.7158. Min Act: -0.0000

Data Index: 1554850 (The Pile)

Max Activating Token Index: 474

Text #17

Max Range: 1.2183. Min Range: -1.2183

Max Act: 0.7263. Min Act: -0.0000

Data Index: 83592 (The Pile)

Max Activating Token Index: 564

Text #18

Max Range: 1.2183. Min Range: -1.2183

Max Act: 0.8269. Min Act: -0.0000

Data Index: 758433 (The Pile)

Max Activating Token Index: 551

Text #19

Max Range: 1.2183. Min Range: -1.2183

Max Act: 0.7181. Min Act: -0.0000

Data Index: 278852 (The Pile)

Max Activating Token Index: 501