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

Dataset: The Pile

Neuron 1617 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: 0.8706. Min Range: -0.8706

Max Act: 0.8706. Min Act: -0.0000

Data Index: 1867880 (The Pile)

Max Activating Token Index: 657

Text #1

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.7454. Min Act: -0.0000

Data Index: 222254 (The Pile)

Max Activating Token Index: 188

Text #2

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.7935. Min Act: -0.0000

Data Index: 166702 (The Pile)

Max Activating Token Index: 61

Text #3

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.8020. Min Act: -0.0000

Data Index: 802971 (The Pile)

Max Activating Token Index: 319

Text #4

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.7692. Min Act: -0.0000

Data Index: 676992 (The Pile)

Max Activating Token Index: 602

Text #5

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.7564. Min Act: -0.0000

Data Index: 503702 (The Pile)

Max Activating Token Index: 807

Text #6

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.6722. Min Act: -0.0000

Data Index: 1887429 (The Pile)

Max Activating Token Index: 628

Text #7

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.7680. Min Act: -0.0000

Data Index: 956654 (The Pile)

Max Activating Token Index: 561

Text #8

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.6475. Min Act: -0.0000

Data Index: 1579794 (The Pile)

Max Activating Token Index: 396

Text #9

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.7096. Min Act: -0.0000

Data Index: 393831 (The Pile)

Max Activating Token Index: 323

Text #10

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.6889. Min Act: -0.0000

Data Index: 1730125 (The Pile)

Max Activating Token Index: 272

Text #11

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.6139. Min Act: -0.0000

Data Index: 1580044 (The Pile)

Max Activating Token Index: 275

Text #12

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.6434. Min Act: -0.0000

Data Index: 658212 (The Pile)

Max Activating Token Index: 749

Text #13

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.6426. Min Act: -0.0000

Data Index: 801323 (The Pile)

Max Activating Token Index: 255

Text #14

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.5818. Min Act: -0.0000

Data Index: 1607356 (The Pile)

Max Activating Token Index: 388

Text #15

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.6145. Min Act: -0.0000

Data Index: 30307 (The Pile)

Max Activating Token Index: 526

Text #16

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.5713. Min Act: -0.0000

Data Index: 1159571 (The Pile)

Max Activating Token Index: 972

Text #17

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.5862. Min Act: -0.0000

Data Index: 1888695 (The Pile)

Max Activating Token Index: 422

Text #18

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.5559. Min Act: -0.0000

Data Index: 1377492 (The Pile)

Max Activating Token Index: 767

Text #19

Max Range: 0.8706. Min Range: -0.8706

Max Act: 0.4976. Min Act: -0.0000

Data Index: 1319089 (The Pile)

Max Activating Token Index: 250