Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 398 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.5988. Min Act: 0.0000

Data Index: 1433467 (The Pile)

Max Activating Token Index: 883

Text #1

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4567. Min Act: -0.0000

Data Index: 768459 (The Pile)

Max Activating Token Index: 939

Text #2

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4318. Min Act: -0.0000

Data Index: 1248719 (The Pile)

Max Activating Token Index: 750

Text #3

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4724. Min Act: -0.0000

Data Index: 1391466 (The Pile)

Max Activating Token Index: 557

Text #4

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4529. Min Act: -0.0000

Data Index: 1306430 (The Pile)

Max Activating Token Index: 210

Text #5

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4384. Min Act: -0.0000

Data Index: 331679 (The Pile)

Max Activating Token Index: 425

Text #6

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4601. Min Act: -0.0000

Data Index: 523206 (The Pile)

Max Activating Token Index: 424

Text #7

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4290. Min Act: -0.0000

Data Index: 167764 (The Pile)

Max Activating Token Index: 503

Text #8

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4356. Min Act: -0.0000

Data Index: 11854 (The Pile)

Max Activating Token Index: 453

Text #9

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4236. Min Act: -0.0000

Data Index: 1798837 (The Pile)

Max Activating Token Index: 950

Text #10

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.3719. Min Act: 0.0000

Data Index: 902620 (The Pile)

Max Activating Token Index: 855

Text #11

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4414. Min Act: -0.0000

Data Index: 528528 (The Pile)

Max Activating Token Index: 191

Text #12

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4021. Min Act: -0.0000

Data Index: 1226075 (The Pile)

Max Activating Token Index: 817

Text #13

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4177. Min Act: -0.0000

Data Index: 1623873 (The Pile)

Max Activating Token Index: 971

Text #14

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4036. Min Act: -0.0000

Data Index: 1374584 (The Pile)

Max Activating Token Index: 437

Text #15

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.4166. Min Act: -0.0000

Data Index: 189114 (The Pile)

Max Activating Token Index: 231

Text #16

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.3959. Min Act: -0.0000

Data Index: 1673216 (The Pile)

Max Activating Token Index: 531

Text #17

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.3980. Min Act: -0.0000

Data Index: 1758324 (The Pile)

Max Activating Token Index: 963

Text #18

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.3997. Min Act: -0.0000

Data Index: 1423649 (The Pile)

Max Activating Token Index: 482

Text #19

Max Range: 0.5988. Min Range: -0.5988

Max Act: 0.3993. Min Act: -0.0000

Data Index: 77954 (The Pile)

Max Activating Token Index: 184