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

Dataset: The Pile

Neuron 2827 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.6768. Min Act: -0.0000

Data Index: 530074 (The Pile)

Max Activating Token Index: 291

Text #1

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.5832. Min Act: -0.0000

Data Index: 76199 (The Pile)

Max Activating Token Index: 290

Text #2

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.5450. Min Act: -0.0000

Data Index: 1068461 (The Pile)

Max Activating Token Index: 521

Text #3

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.4723. Min Act: -0.0000

Data Index: 826436 (The Pile)

Max Activating Token Index: 694

Text #4

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.4898. Min Act: -0.0000

Data Index: 702941 (The Pile)

Max Activating Token Index: 285

Text #5

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.5029. Min Act: -0.0000

Data Index: 1988227 (The Pile)

Max Activating Token Index: 991

Text #6

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.4871. Min Act: -0.0000

Data Index: 1278969 (The Pile)

Max Activating Token Index: 644

Text #7

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.4789. Min Act: -0.0000

Data Index: 1856805 (The Pile)

Max Activating Token Index: 805

Text #8

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.4288. Min Act: -0.0000

Data Index: 537458 (The Pile)

Max Activating Token Index: 288

Text #9

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.4457. Min Act: -0.0000

Data Index: 1291636 (The Pile)

Max Activating Token Index: 858

Text #10

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.4387. Min Act: -0.0000

Data Index: 1872859 (The Pile)

Max Activating Token Index: 127

Text #11

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.4636. Min Act: -0.0000

Data Index: 1716408 (The Pile)

Max Activating Token Index: 407

Text #12

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.4505. Min Act: -0.0000

Data Index: 25107 (The Pile)

Max Activating Token Index: 33

Text #13

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.4371. Min Act: -0.0000

Data Index: 1463444 (The Pile)

Max Activating Token Index: 570

Text #14

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.4260. Min Act: -0.0000

Data Index: 1937936 (The Pile)

Max Activating Token Index: 654

Text #15

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.4296. Min Act: -0.0000

Data Index: 1649001 (The Pile)

Max Activating Token Index: 308

Text #16

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.4108. Min Act: -0.0000

Data Index: 162236 (The Pile)

Max Activating Token Index: 415

Text #17

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.3323. Min Act: -0.0000

Data Index: 978921 (The Pile)

Max Activating Token Index: 659

Text #18

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.4368. Min Act: -0.0000

Data Index: 1574630 (The Pile)

Max Activating Token Index: 544

Text #19

Max Range: 0.6768. Min Range: -0.6768

Max Act: 0.3971. Min Act: -0.0000

Data Index: 277904 (The Pile)

Max Activating Token Index: 287