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

Dataset: The Pile

Neuron 1289 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6166. Min Range: -0.6166

Max Act: 0.6166. Min Act: -0.0000

Data Index: 1533479 (The Pile)

Max Activating Token Index: 232

Text #1

Max Range: 0.6166. Min Range: -0.6166

Max Act: 0.4894. Min Act: -0.0000

Data Index: 1257888 (The Pile)

Max Activating Token Index: 283

Text #2

Max Range: 0.6166. Min Range: -0.6166

Max Act: 0.5513. Min Act: -0.0000

Data Index: 1006790 (The Pile)

Max Activating Token Index: 1009

Text #3

Max Range: 0.6166. Min Range: -0.6166

Max Act: 0.4772. Min Act: -0.0000

Data Index: 913142 (The Pile)

Max Activating Token Index: 619

Text #4

Max Range: 0.6166. Min Range: -0.6166

Max Act: 0.4185. Min Act: -0.0000

Data Index: 1701756 (The Pile)

Max Activating Token Index: 291

Text #5

Max Range: 0.6166. Min Range: -0.6166

Max Act: 0.4146. Min Act: -0.0000

Data Index: 6200 (The Pile)

Max Activating Token Index: 137

Text #6

Max Range: 0.6166. Min Range: -0.6166

Max Act: 0.4330. Min Act: -0.0000

Data Index: 509490 (The Pile)

Max Activating Token Index: 613

Text #7

Max Range: 0.6166. Min Range: -0.6166

Max Act: 0.4003. Min Act: -0.0000

Data Index: 1959434 (The Pile)

Max Activating Token Index: 158

Text #8

Max Range: 0.6166. Min Range: -0.6166

Max Act: 0.3908. Min Act: -0.0000

Data Index: 380574 (The Pile)

Max Activating Token Index: 110

Text #9

Max Range: 0.6166. Min Range: -0.6166

Max Act: 0.3916. Min Act: -0.0000

Data Index: 693260 (The Pile)

Max Activating Token Index: 226

Text #10

Max Range: 0.6166. Min Range: -0.6166

Max Act: 0.4004. Min Act: -0.0000

Data Index: 1797634 (The Pile)

Max Activating Token Index: 231

Text #11

Max Range: 0.6166. Min Range: -0.6166

Max Act: 0.3897. Min Act: -0.0000

Data Index: 30237 (The Pile)

Max Activating Token Index: 447

Text #12

Max Range: 0.6166. Min Range: -0.6166

Max Act: 0.3788. Min Act: -0.0000

Data Index: 1878253 (The Pile)

Max Activating Token Index: 617

Text #13

Max Range: 0.6166. Min Range: -0.6166

Max Act: 0.3744. Min Act: -0.0000

Data Index: 137944 (The Pile)

Max Activating Token Index: 222

Text #14

Max Range: 0.6166. Min Range: -0.6166

Max Act: 0.3696. Min Act: -0.0000

Data Index: 1059342 (The Pile)

Max Activating Token Index: 206

Text #15

Max Range: 0.6166. Min Range: -0.6166

Max Act: 0.3545. Min Act: -0.0000

Data Index: 1077565 (The Pile)

Max Activating Token Index: 901

Text #16

Max Range: 0.6166. Min Range: -0.6166

Max Act: 0.3441. Min Act: -0.0000

Data Index: 530204 (The Pile)

Max Activating Token Index: 615

Text #17

Max Range: 0.6166. Min Range: -0.6166

Max Act: 0.3511. Min Act: -0.0000

Data Index: 1762849 (The Pile)

Max Activating Token Index: 905

Text #18

Max Range: 0.6166. Min Range: -0.6166

Max Act: 0.3683. Min Act: -0.0000

Data Index: 785172 (The Pile)

Max Activating Token Index: 388

Text #19

Max Range: 0.6166. Min Range: -0.6166

Max Act: 0.3622. Min Act: -0.0000

Data Index: 703588 (The Pile)

Max Activating Token Index: 242