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

Dataset: The Pile

Neuron 479 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2079. Min Range: -3.2079

Max Act: 3.2079. Min Act: -0.0000

Data Index: 1385090 (The Pile)

Max Activating Token Index: 399

Text #1

Max Range: 3.2079. Min Range: -3.2079

Max Act: 2.3275. Min Act: -0.0000

Data Index: 904807 (The Pile)

Max Activating Token Index: 698

Text #2

Max Range: 3.2079. Min Range: -3.2079

Max Act: 2.1745. Min Act: -0.0000

Data Index: 1236263 (The Pile)

Max Activating Token Index: 302

Text #3

Max Range: 3.2079. Min Range: -3.2079

Max Act: 2.1352. Min Act: -0.0000

Data Index: 820789 (The Pile)

Max Activating Token Index: 661

Text #4

Max Range: 3.2079. Min Range: -3.2079

Max Act: 1.9465. Min Act: -0.0000

Data Index: 1822611 (The Pile)

Max Activating Token Index: 579

Text #5

Max Range: 3.2079. Min Range: -3.2079

Max Act: 2.1253. Min Act: -0.0000

Data Index: 517898 (The Pile)

Max Activating Token Index: 978

Text #6

Max Range: 3.2079. Min Range: -3.2079

Max Act: 1.9718. Min Act: -0.0000

Data Index: 99341 (The Pile)

Max Activating Token Index: 696

Text #7

Max Range: 3.2079. Min Range: -3.2079

Max Act: 1.9571. Min Act: -0.0000

Data Index: 185226 (The Pile)

Max Activating Token Index: 581

Text #8

Max Range: 3.2079. Min Range: -3.2079

Max Act: 1.9487. Min Act: -0.0000

Data Index: 1253253 (The Pile)

Max Activating Token Index: 157

Text #9

Max Range: 3.2079. Min Range: -3.2079

Max Act: 2.0464. Min Act: -0.0000

Data Index: 991806 (The Pile)

Max Activating Token Index: 405

Text #10

Max Range: 3.2079. Min Range: -3.2079

Max Act: 2.0403. Min Act: -0.0000

Data Index: 886858 (The Pile)

Max Activating Token Index: 480

Text #11

Max Range: 3.2079. Min Range: -3.2079

Max Act: 2.1388. Min Act: -0.0000

Data Index: 1023119 (The Pile)

Max Activating Token Index: 996

Text #12

Max Range: 3.2079. Min Range: -3.2079

Max Act: 1.9954. Min Act: -0.0000

Data Index: 443019 (The Pile)

Max Activating Token Index: 112

Text #13

Max Range: 3.2079. Min Range: -3.2079

Max Act: 1.8562. Min Act: -0.0000

Data Index: 547716 (The Pile)

Max Activating Token Index: 256

Text #14

Max Range: 3.2079. Min Range: -3.2079

Max Act: 1.9498. Min Act: -0.0000

Data Index: 1178899 (The Pile)

Max Activating Token Index: 124

Text #15

Max Range: 3.2079. Min Range: -3.2079

Max Act: 1.9496. Min Act: -0.0000

Data Index: 1228873 (The Pile)

Max Activating Token Index: 289

Text #16

Max Range: 3.2079. Min Range: -3.2079

Max Act: 1.8386. Min Act: -0.0000

Data Index: 194764 (The Pile)

Max Activating Token Index: 274

Text #17

Max Range: 3.2079. Min Range: -3.2079

Max Act: 1.8358. Min Act: -0.0000

Data Index: 1532132 (The Pile)

Max Activating Token Index: 184

Text #18

Max Range: 3.2079. Min Range: -3.2079

Max Act: 1.9253. Min Act: -0.0000

Data Index: 659080 (The Pile)

Max Activating Token Index: 99

Text #19

Max Range: 3.2079. Min Range: -3.2079

Max Act: 1.8127. Min Act: -0.0000

Data Index: 135814 (The Pile)

Max Activating Token Index: 127