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

Dataset: The Pile

Neuron 2718 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4874. Min Act: -0.0000

Data Index: 732804 (The Pile)

Max Activating Token Index: 353

Text #1

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4670. Min Act: -0.0000

Data Index: 1913645 (The Pile)

Max Activating Token Index: 446

Text #2

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4536. Min Act: -0.0000

Data Index: 575352 (The Pile)

Max Activating Token Index: 473

Text #3

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4185. Min Act: -0.0000

Data Index: 1072668 (The Pile)

Max Activating Token Index: 368

Text #4

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3778. Min Act: -0.0000

Data Index: 1652693 (The Pile)

Max Activating Token Index: 514

Text #5

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3628. Min Act: -0.0000

Data Index: 660236 (The Pile)

Max Activating Token Index: 952

Text #6

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3629. Min Act: -0.0000

Data Index: 9107 (The Pile)

Max Activating Token Index: 54

Text #7

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3712. Min Act: -0.0000

Data Index: 1698371 (The Pile)

Max Activating Token Index: 131

Text #8

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3647. Min Act: -0.0000

Data Index: 179822 (The Pile)

Max Activating Token Index: 84

Text #9

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3539. Min Act: -0.0000

Data Index: 1639794 (The Pile)

Max Activating Token Index: 190

Text #10

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3498. Min Act: -0.0000

Data Index: 223850 (The Pile)

Max Activating Token Index: 447

Text #11

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3457. Min Act: -0.0000

Data Index: 359372 (The Pile)

Max Activating Token Index: 437

Text #12

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3541. Min Act: -0.0000

Data Index: 1773292 (The Pile)

Max Activating Token Index: 32

Text #13

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3407. Min Act: 0.0002

Data Index: 1816588 (The Pile)

Max Activating Token Index: 116

Text #14

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3208. Min Act: -0.0000

Data Index: 175639 (The Pile)

Max Activating Token Index: 533

Text #15

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3279. Min Act: -0.0000

Data Index: 864555 (The Pile)

Max Activating Token Index: 481

Text #16

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3286. Min Act: -0.0000

Data Index: 1186936 (The Pile)

Max Activating Token Index: 586

Text #17

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3212. Min Act: -0.0000

Data Index: 1733534 (The Pile)

Max Activating Token Index: 807

Text #18

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.2930. Min Act: -0.0000

Data Index: 506471 (The Pile)

Max Activating Token Index: 920

Text #19

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3043. Min Act: -0.0000

Data Index: 1355430 (The Pile)

Max Activating Token Index: 412