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

Dataset: The Pile

Neuron 3434 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3405. Min Range: -1.3405

Max Act: 1.3405. Min Act: -0.0000

Data Index: 620150 (The Pile)

Max Activating Token Index: 906

Text #1

Max Range: 1.3405. Min Range: -1.3405

Max Act: 1.1234. Min Act: -0.0000

Data Index: 1745499 (The Pile)

Max Activating Token Index: 356

Text #2

Max Range: 1.3405. Min Range: -1.3405

Max Act: 1.1418. Min Act: -0.0000

Data Index: 1067768 (The Pile)

Max Activating Token Index: 934

Text #3

Max Range: 1.3405. Min Range: -1.3405

Max Act: 1.0815. Min Act: -0.0000

Data Index: 1038932 (The Pile)

Max Activating Token Index: 952

Text #4

Max Range: 1.3405. Min Range: -1.3405

Max Act: 1.1212. Min Act: -0.0000

Data Index: 103572 (The Pile)

Max Activating Token Index: 392

Text #5

Max Range: 1.3405. Min Range: -1.3405

Max Act: 1.0314. Min Act: -0.0000

Data Index: 957958 (The Pile)

Max Activating Token Index: 184

Text #6

Max Range: 1.3405. Min Range: -1.3405

Max Act: 1.0315. Min Act: -0.0000

Data Index: 1419032 (The Pile)

Max Activating Token Index: 441

Text #7

Max Range: 1.3405. Min Range: -1.3405

Max Act: 1.0179. Min Act: -0.0000

Data Index: 1132874 (The Pile)

Max Activating Token Index: 192

Text #8

Max Range: 1.3405. Min Range: -1.3405

Max Act: 1.0780. Min Act: -0.0000

Data Index: 165555 (The Pile)

Max Activating Token Index: 147

Text #9

Max Range: 1.3405. Min Range: -1.3405

Max Act: 0.9973. Min Act: -0.0000

Data Index: 348160 (The Pile)

Max Activating Token Index: 404

Text #10

Max Range: 1.3405. Min Range: -1.3405

Max Act: 1.0421. Min Act: -0.0000

Data Index: 1949571 (The Pile)

Max Activating Token Index: 257

Text #11

Max Range: 1.3405. Min Range: -1.3405

Max Act: 1.0085. Min Act: -0.0000

Data Index: 521055 (The Pile)

Max Activating Token Index: 890

Text #12

Max Range: 1.3405. Min Range: -1.3405

Max Act: 0.9791. Min Act: -0.0000

Data Index: 1067435 (The Pile)

Max Activating Token Index: 91

Text #13

Max Range: 1.3405. Min Range: -1.3405

Max Act: 1.0026. Min Act: -0.0000

Data Index: 992178 (The Pile)

Max Activating Token Index: 482

Text #14

Max Range: 1.3405. Min Range: -1.3405

Max Act: 0.9910. Min Act: -0.0000

Data Index: 1470727 (The Pile)

Max Activating Token Index: 981

Text #15

Max Range: 1.3405. Min Range: -1.3405

Max Act: 1.0383. Min Act: -0.0000

Data Index: 1443191 (The Pile)

Max Activating Token Index: 299

Text #16

Max Range: 1.3405. Min Range: -1.3405

Max Act: 0.9999. Min Act: -0.0000

Data Index: 541511 (The Pile)

Max Activating Token Index: 608

Text #17

Max Range: 1.3405. Min Range: -1.3405

Max Act: 0.9080. Min Act: -0.0000

Data Index: 1118318 (The Pile)

Max Activating Token Index: 180

Text #18

Max Range: 1.3405. Min Range: -1.3405

Max Act: 0.9902. Min Act: -0.0000

Data Index: 727438 (The Pile)

Max Activating Token Index: 506

Text #19

Max Range: 1.3405. Min Range: -1.3405

Max Act: 0.9536. Min Act: -0.0000

Data Index: 516003 (The Pile)

Max Activating Token Index: 198