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

Dataset: The Pile

Neuron 1005 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: 1.3273. Min Range: -1.3273

Max Act: 1.3273. Min Act: -0.0000

Data Index: 575898 (The Pile)

Max Activating Token Index: 536

Text #1

Max Range: 1.3273. Min Range: -1.3273

Max Act: 1.2957. Min Act: -0.0000

Data Index: 1967676 (The Pile)

Max Activating Token Index: 677

Text #2

Max Range: 1.3273. Min Range: -1.3273

Max Act: 1.1464. Min Act: -0.0000

Data Index: 376286 (The Pile)

Max Activating Token Index: 578

Text #3

Max Range: 1.3273. Min Range: -1.3273

Max Act: 1.1667. Min Act: -0.0000

Data Index: 108407 (The Pile)

Max Activating Token Index: 624

Text #4

Max Range: 1.3273. Min Range: -1.3273

Max Act: 1.1350. Min Act: -0.0000

Data Index: 406443 (The Pile)

Max Activating Token Index: 477

Text #5

Max Range: 1.3273. Min Range: -1.3273

Max Act: 1.1175. Min Act: -0.0000

Data Index: 1463152 (The Pile)

Max Activating Token Index: 777

Text #6

Max Range: 1.3273. Min Range: -1.3273

Max Act: 1.1398. Min Act: -0.0000

Data Index: 1204323 (The Pile)

Max Activating Token Index: 1020

Text #7

Max Range: 1.3273. Min Range: -1.3273

Max Act: 1.1326. Min Act: -0.0000

Data Index: 1319301 (The Pile)

Max Activating Token Index: 647

Text #8

Max Range: 1.3273. Min Range: -1.3273

Max Act: 1.0749. Min Act: -0.0000

Data Index: 535257 (The Pile)

Max Activating Token Index: 143

Text #9

Max Range: 1.3273. Min Range: -1.3273

Max Act: 1.0951. Min Act: -0.0000

Data Index: 474165 (The Pile)

Max Activating Token Index: 851

Text #10

Max Range: 1.3273. Min Range: -1.3273

Max Act: 1.0697. Min Act: -0.0000

Data Index: 1882767 (The Pile)

Max Activating Token Index: 660

Text #11

Max Range: 1.3273. Min Range: -1.3273

Max Act: 1.0885. Min Act: -0.0000

Data Index: 1110313 (The Pile)

Max Activating Token Index: 921

Text #12

Max Range: 1.3273. Min Range: -1.3273

Max Act: 1.0523. Min Act: -0.0000

Data Index: 1805302 (The Pile)

Max Activating Token Index: 311

Text #13

Max Range: 1.3273. Min Range: -1.3273

Max Act: 1.1153. Min Act: -0.0000

Data Index: 1527326 (The Pile)

Max Activating Token Index: 861

Text #14

Max Range: 1.3273. Min Range: -1.3273

Max Act: 0.9872. Min Act: -0.0000

Data Index: 1667936 (The Pile)

Max Activating Token Index: 483

Text #15

Max Range: 1.3273. Min Range: -1.3273

Max Act: 1.0337. Min Act: -0.0000

Data Index: 1435712 (The Pile)

Max Activating Token Index: 825

Text #16

Max Range: 1.3273. Min Range: -1.3273

Max Act: 1.0444. Min Act: -0.0000

Data Index: 1256286 (The Pile)

Max Activating Token Index: 159

Text #17

Max Range: 1.3273. Min Range: -1.3273

Max Act: 1.0617. Min Act: -0.0000

Data Index: 615443 (The Pile)

Max Activating Token Index: 888

Text #18

Max Range: 1.3273. Min Range: -1.3273

Max Act: 1.0897. Min Act: -0.0000

Data Index: 1263093 (The Pile)

Max Activating Token Index: 792

Text #19

Max Range: 1.3273. Min Range: -1.3273

Max Act: 1.0544. Min Act: -0.0000

Data Index: 1237902 (The Pile)

Max Activating Token Index: 326