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

Dataset: The Pile

Neuron 1 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: 0.5445. Min Range: -0.5445

Max Act: 0.5438. Min Act: 0.0001

Data Index: 1653487 (The Pile)

Max Activating Token Index: 487

Text #1

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.5445. Min Act: -0.0000

Data Index: 623147 (The Pile)

Max Activating Token Index: 414

Text #2

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4972. Min Act: -0.0000

Data Index: 484637 (The Pile)

Max Activating Token Index: 125

Text #3

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.5005. Min Act: -0.0000

Data Index: 1732960 (The Pile)

Max Activating Token Index: 374

Text #4

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.5012. Min Act: -0.0000

Data Index: 1340802 (The Pile)

Max Activating Token Index: 260

Text #5

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4532. Min Act: -0.0000

Data Index: 1025479 (The Pile)

Max Activating Token Index: 568

Text #6

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4754. Min Act: -0.0000

Data Index: 1024747 (The Pile)

Max Activating Token Index: 441

Text #7

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4850. Min Act: -0.0000

Data Index: 1441047 (The Pile)

Max Activating Token Index: 946

Text #8

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4477. Min Act: -0.0000

Data Index: 1981214 (The Pile)

Max Activating Token Index: 852

Text #9

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4448. Min Act: -0.0000

Data Index: 88432 (The Pile)

Max Activating Token Index: 802

Text #10

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4843. Min Act: -0.0000

Data Index: 389721 (The Pile)

Max Activating Token Index: 324

Text #11

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4688. Min Act: -0.0000

Data Index: 857141 (The Pile)

Max Activating Token Index: 955

Text #12

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4249. Min Act: -0.0000

Data Index: 1988155 (The Pile)

Max Activating Token Index: 500

Text #13

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4237. Min Act: -0.0000

Data Index: 1708293 (The Pile)

Max Activating Token Index: 100

Text #14

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.3956. Min Act: -0.0000

Data Index: 1982560 (The Pile)

Max Activating Token Index: 94

Text #15

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4530. Min Act: -0.0000

Data Index: 1459255 (The Pile)

Max Activating Token Index: 786

Text #16

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4499. Min Act: -0.0000

Data Index: 417853 (The Pile)

Max Activating Token Index: 894

Text #17

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4209. Min Act: -0.0000

Data Index: 1305296 (The Pile)

Max Activating Token Index: 710

Text #18

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4466. Min Act: -0.0000

Data Index: 311948 (The Pile)

Max Activating Token Index: 741

Text #19

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4508. Min Act: -0.0000

Data Index: 575569 (The Pile)

Max Activating Token Index: 394