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

Dataset: The Pile

Neuron 681 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: 0.7861. Min Range: -0.7861

Max Act: 0.7861. Min Act: -0.0000

Data Index: 125532 (The Pile)

Max Activating Token Index: 611

Text #1

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.7823. Min Act: -0.0000

Data Index: 641762 (The Pile)

Max Activating Token Index: 133

Text #2

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.7683. Min Act: -0.0000

Data Index: 295339 (The Pile)

Max Activating Token Index: 364

Text #3

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.7770. Min Act: -0.0000

Data Index: 1161765 (The Pile)

Max Activating Token Index: 522

Text #4

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.7274. Min Act: -0.0000

Data Index: 1302821 (The Pile)

Max Activating Token Index: 607

Text #5

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.7338. Min Act: -0.0000

Data Index: 1105023 (The Pile)

Max Activating Token Index: 554

Text #6

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.7329. Min Act: -0.0000

Data Index: 87861 (The Pile)

Max Activating Token Index: 337

Text #7

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.7310. Min Act: -0.0000

Data Index: 1809801 (The Pile)

Max Activating Token Index: 720

Text #8

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.6834. Min Act: -0.0000

Data Index: 742258 (The Pile)

Max Activating Token Index: 612

Text #9

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.6901. Min Act: -0.0000

Data Index: 601101 (The Pile)

Max Activating Token Index: 608

Text #10

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.6608. Min Act: -0.0000

Data Index: 829765 (The Pile)

Max Activating Token Index: 504

Text #11

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.6261. Min Act: -0.0000

Data Index: 1785519 (The Pile)

Max Activating Token Index: 493

Text #12

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.6216. Min Act: -0.0000

Data Index: 1626307 (The Pile)

Max Activating Token Index: 832

Text #13

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.6428. Min Act: -0.0000

Data Index: 1649797 (The Pile)

Max Activating Token Index: 384

Text #14

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.6541. Min Act: -0.0000

Data Index: 40500 (The Pile)

Max Activating Token Index: 407

Text #15

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.6430. Min Act: -0.0000

Data Index: 287875 (The Pile)

Max Activating Token Index: 577

Text #16

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.6738. Min Act: -0.0000

Data Index: 1791237 (The Pile)

Max Activating Token Index: 499

Text #17

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.5982. Min Act: -0.0000

Data Index: 903540 (The Pile)

Max Activating Token Index: 452

Text #18

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.6280. Min Act: -0.0000

Data Index: 166964 (The Pile)

Max Activating Token Index: 804

Text #19

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.6103. Min Act: -0.0000

Data Index: 1019051 (The Pile)

Max Activating Token Index: 343