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

Dataset: The Pile

Neuron 2265 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: 1.0265. Min Range: -1.0265

Max Act: 1.0051. Min Act: -0.0000

Data Index: 680444 (The Pile)

Max Activating Token Index: 619

Text #1

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.8970. Min Act: -0.0000

Data Index: 1531407 (The Pile)

Max Activating Token Index: 778

Text #2

Max Range: 1.0265. Min Range: -1.0265

Max Act: 1.0265. Min Act: -0.0000

Data Index: 591204 (The Pile)

Max Activating Token Index: 295

Text #3

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.9242. Min Act: -0.0000

Data Index: 831289 (The Pile)

Max Activating Token Index: 204

Text #4

Max Range: 1.0265. Min Range: -1.0265

Max Act: 1.0039. Min Act: -0.0000

Data Index: 1875654 (The Pile)

Max Activating Token Index: 539

Text #5

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.9261. Min Act: -0.0000

Data Index: 903356 (The Pile)

Max Activating Token Index: 437

Text #6

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.9416. Min Act: -0.0000

Data Index: 886208 (The Pile)

Max Activating Token Index: 635

Text #7

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.9392. Min Act: -0.0000

Data Index: 709178 (The Pile)

Max Activating Token Index: 64

Text #8

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.9127. Min Act: -0.0000

Data Index: 153366 (The Pile)

Max Activating Token Index: 77

Text #9

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.9490. Min Act: -0.0000

Data Index: 1067803 (The Pile)

Max Activating Token Index: 555

Text #10

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.8518. Min Act: -0.0000

Data Index: 205707 (The Pile)

Max Activating Token Index: 740

Text #11

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.8706. Min Act: -0.0000

Data Index: 1745831 (The Pile)

Max Activating Token Index: 623

Text #12

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.8074. Min Act: -0.0000

Data Index: 1044781 (The Pile)

Max Activating Token Index: 161

Text #13

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.8383. Min Act: -0.0000

Data Index: 899600 (The Pile)

Max Activating Token Index: 475

Text #14

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.8593. Min Act: -0.0000

Data Index: 537037 (The Pile)

Max Activating Token Index: 381

Text #15

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.7987. Min Act: -0.0000

Data Index: 226992 (The Pile)

Max Activating Token Index: 259

Text #16

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.7970. Min Act: -0.0000

Data Index: 1934584 (The Pile)

Max Activating Token Index: 676

Text #17

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.7680. Min Act: -0.0000

Data Index: 885504 (The Pile)

Max Activating Token Index: 449

Text #18

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.8479. Min Act: -0.0000

Data Index: 871447 (The Pile)

Max Activating Token Index: 84

Text #19

Max Range: 1.0265. Min Range: -1.0265

Max Act: 0.9143. Min Act: -0.0000

Data Index: 1159678 (The Pile)

Max Activating Token Index: 673