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

Dataset: The Pile

Neuron 1612 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.9952. Min Act: -0.0000

Data Index: 1626274 (The Pile)

Max Activating Token Index: 54

Text #1

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.8515. Min Act: -0.0000

Data Index: 806333 (The Pile)

Max Activating Token Index: 946

Text #2

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.8174. Min Act: -0.0000

Data Index: 1070826 (The Pile)

Max Activating Token Index: 813

Text #3

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.7668. Min Act: -0.0000

Data Index: 807481 (The Pile)

Max Activating Token Index: 417

Text #4

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.7148. Min Act: -0.0000

Data Index: 1149425 (The Pile)

Max Activating Token Index: 712

Text #5

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.7039. Min Act: -0.0000

Data Index: 1181598 (The Pile)

Max Activating Token Index: 543

Text #6

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.7049. Min Act: -0.0000

Data Index: 388038 (The Pile)

Max Activating Token Index: 760

Text #7

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.6768. Min Act: 0.0000

Data Index: 528758 (The Pile)

Max Activating Token Index: 970

Text #8

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.6757. Min Act: -0.0000

Data Index: 1961558 (The Pile)

Max Activating Token Index: 157

Text #9

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.6420. Min Act: -0.0000

Data Index: 26999 (The Pile)

Max Activating Token Index: 276

Text #10

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.6584. Min Act: -0.0000

Data Index: 592010 (The Pile)

Max Activating Token Index: 646

Text #11

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.6297. Min Act: -0.0000

Data Index: 668172 (The Pile)

Max Activating Token Index: 586

Text #12

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.6492. Min Act: -0.0000

Data Index: 1013167 (The Pile)

Max Activating Token Index: 532

Text #13

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.6428. Min Act: -0.0000

Data Index: 872233 (The Pile)

Max Activating Token Index: 986

Text #14

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.6331. Min Act: 0.0000

Data Index: 1198870 (The Pile)

Max Activating Token Index: 267

Text #15

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.6148. Min Act: -0.0000

Data Index: 1394181 (The Pile)

Max Activating Token Index: 23

Text #16

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.5948. Min Act: -0.0000

Data Index: 479026 (The Pile)

Max Activating Token Index: 718

Text #17

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.6150. Min Act: -0.0000

Data Index: 530572 (The Pile)

Max Activating Token Index: 326

Text #18

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.5860. Min Act: -0.0000

Data Index: 1818304 (The Pile)

Max Activating Token Index: 537

Text #19

Max Range: 0.9952. Min Range: -0.9952

Max Act: 0.6459. Min Act: -0.0000

Data Index: 93750 (The Pile)

Max Activating Token Index: 535