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

Dataset: The Pile

Neuron 3024 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1445. Min Range: -1.1445

Max Act: 1.1445. Min Act: -0.0000

Data Index: 1864255 (The Pile)

Max Activating Token Index: 851

Text #1

Max Range: 1.1445. Min Range: -1.1445

Max Act: 0.9838. Min Act: -0.0000

Data Index: 556597 (The Pile)

Max Activating Token Index: 753

Text #2

Max Range: 1.1445. Min Range: -1.1445

Max Act: 1.0807. Min Act: -0.0000

Data Index: 1176773 (The Pile)

Max Activating Token Index: 849

Text #3

Max Range: 1.1445. Min Range: -1.1445

Max Act: 1.0811. Min Act: -0.0000

Data Index: 431235 (The Pile)

Max Activating Token Index: 505

Text #4

Max Range: 1.1445. Min Range: -1.1445

Max Act: 1.1441. Min Act: -0.0000

Data Index: 1915935 (The Pile)

Max Activating Token Index: 433

Text #5

Max Range: 1.1445. Min Range: -1.1445

Max Act: 1.1321. Min Act: -0.0000

Data Index: 621042 (The Pile)

Max Activating Token Index: 642

Text #6

Max Range: 1.1445. Min Range: -1.1445

Max Act: 0.9837. Min Act: -0.0000

Data Index: 1080745 (The Pile)

Max Activating Token Index: 604

Text #7

Max Range: 1.1445. Min Range: -1.1445

Max Act: 0.9334. Min Act: -0.0000

Data Index: 930885 (The Pile)

Max Activating Token Index: 369

Text #8

Max Range: 1.1445. Min Range: -1.1445

Max Act: 0.8139. Min Act: -0.0000

Data Index: 100514 (The Pile)

Max Activating Token Index: 185

Text #9

Max Range: 1.1445. Min Range: -1.1445

Max Act: 0.8514. Min Act: -0.0000

Data Index: 745482 (The Pile)

Max Activating Token Index: 708

Text #10

Max Range: 1.1445. Min Range: -1.1445

Max Act: 0.7748. Min Act: -0.0000

Data Index: 222055 (The Pile)

Max Activating Token Index: 845

Text #11

Max Range: 1.1445. Min Range: -1.1445

Max Act: 0.7969. Min Act: -0.0000

Data Index: 306840 (The Pile)

Max Activating Token Index: 245

Text #12

Max Range: 1.1445. Min Range: -1.1445

Max Act: 0.7689. Min Act: -0.0000

Data Index: 221213 (The Pile)

Max Activating Token Index: 578

Text #13

Max Range: 1.1445. Min Range: -1.1445

Max Act: 0.7041. Min Act: -0.0000

Data Index: 87464 (The Pile)

Max Activating Token Index: 613

Text #14

Max Range: 1.1445. Min Range: -1.1445

Max Act: 0.6822. Min Act: -0.0000

Data Index: 623198 (The Pile)

Max Activating Token Index: 31

Text #15

Max Range: 1.1445. Min Range: -1.1445

Max Act: 0.6932. Min Act: -0.0000

Data Index: 1591849 (The Pile)

Max Activating Token Index: 971

Text #16

Max Range: 1.1445. Min Range: -1.1445

Max Act: 0.5961. Min Act: -0.0000

Data Index: 82449 (The Pile)

Max Activating Token Index: 663

Text #17

Max Range: 1.1445. Min Range: -1.1445

Max Act: 0.6967. Min Act: -0.0000

Data Index: 317447 (The Pile)

Max Activating Token Index: 245

Text #18

Max Range: 1.1445. Min Range: -1.1445

Max Act: 0.6349. Min Act: -0.0000

Data Index: 1399538 (The Pile)

Max Activating Token Index: 311

Text #19

Max Range: 1.1445. Min Range: -1.1445

Max Act: 0.6444. Min Act: -0.0000

Data Index: 194850 (The Pile)

Max Activating Token Index: 928