Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3752 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.6429. Min Act: -0.0001

Data Index: 1129877 (The Pile)

Max Activating Token Index: 525

Text #1

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.8320. Min Act: -0.0001

Data Index: 954286 (The Pile)

Max Activating Token Index: 310

Text #2

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.5069. Min Act: -0.0001

Data Index: 702250 (The Pile)

Max Activating Token Index: 938

Text #3

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.6669. Min Act: -0.0001

Data Index: 1408870 (The Pile)

Max Activating Token Index: 969

Text #4

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.5743. Min Act: -0.0001

Data Index: 945344 (The Pile)

Max Activating Token Index: 758

Text #5

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.5041. Min Act: -0.0001

Data Index: 195850 (The Pile)

Max Activating Token Index: 423

Text #6

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.3764. Min Act: -0.0001

Data Index: 1276881 (The Pile)

Max Activating Token Index: 983

Text #7

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.4679. Min Act: -0.0001

Data Index: 725292 (The Pile)

Max Activating Token Index: 21

Text #8

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.3740. Min Act: -0.0001

Data Index: 323957 (The Pile)

Max Activating Token Index: 422

Text #9

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.4403. Min Act: -0.0001

Data Index: 1358870 (The Pile)

Max Activating Token Index: 720

Text #10

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.4162. Min Act: -0.0001

Data Index: 769891 (The Pile)

Max Activating Token Index: 103

Text #11

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.4401. Min Act: -0.0001

Data Index: 168831 (The Pile)

Max Activating Token Index: 483

Text #12

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.2395. Min Act: -0.0001

Data Index: 671814 (The Pile)

Max Activating Token Index: 651

Text #13

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.3395. Min Act: -0.0001

Data Index: 410552 (The Pile)

Max Activating Token Index: 325

Text #14

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.3213. Min Act: -0.0001

Data Index: 961306 (The Pile)

Max Activating Token Index: 610

Text #15

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.5043. Min Act: -0.0001

Data Index: 82707 (The Pile)

Max Activating Token Index: 749

Text #16

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.3197. Min Act: -0.0001

Data Index: 515304 (The Pile)

Max Activating Token Index: 793

Text #17

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.3802. Min Act: -0.0001

Data Index: 960896 (The Pile)

Max Activating Token Index: 194

Text #18

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.2735. Min Act: -0.0001

Data Index: 579379 (The Pile)

Max Activating Token Index: 447

Text #19

Max Range: 1.8320. Min Range: -1.8320

Max Act: 1.4023. Min Act: -0.0001

Data Index: 7746 (The Pile)

Max Activating Token Index: 369