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

Dataset: The Pile

Neuron 4129 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: 1.6548. Min Range: -1.6548

Max Act: 1.4901. Min Act: -0.0000

Data Index: 1703275 (The Pile)

Max Activating Token Index: 934

Text #1

Max Range: 1.6548. Min Range: -1.6548

Max Act: 1.5586. Min Act: -0.0000

Data Index: 540097 (The Pile)

Max Activating Token Index: 794

Text #2

Max Range: 1.6548. Min Range: -1.6548

Max Act: 1.3052. Min Act: -0.0000

Data Index: 182681 (The Pile)

Max Activating Token Index: 915

Text #3

Max Range: 1.6548. Min Range: -1.6548

Max Act: 1.5313. Min Act: -0.0000

Data Index: 210820 (The Pile)

Max Activating Token Index: 536

Text #4

Max Range: 1.6548. Min Range: -1.6548

Max Act: 1.3283. Min Act: -0.0000

Data Index: 172291 (The Pile)

Max Activating Token Index: 495

Text #5

Max Range: 1.6548. Min Range: -1.6548

Max Act: 1.6548. Min Act: -0.0000

Data Index: 1079542 (The Pile)

Max Activating Token Index: 450

Text #6

Max Range: 1.6548. Min Range: -1.6548

Max Act: 1.3846. Min Act: -0.0000

Data Index: 1235082 (The Pile)

Max Activating Token Index: 620

Text #7

Max Range: 1.6548. Min Range: -1.6548

Max Act: 1.4481. Min Act: -0.0000

Data Index: 92714 (The Pile)

Max Activating Token Index: 950

Text #8

Max Range: 1.6548. Min Range: -1.6548

Max Act: 1.3817. Min Act: -0.0000

Data Index: 1152653 (The Pile)

Max Activating Token Index: 374

Text #9

Max Range: 1.6548. Min Range: -1.6548

Max Act: 1.1866. Min Act: -0.0000

Data Index: 671825 (The Pile)

Max Activating Token Index: 433

Text #10

Max Range: 1.6548. Min Range: -1.6548

Max Act: 1.4500. Min Act: -0.0000

Data Index: 789383 (The Pile)

Max Activating Token Index: 759

Text #11

Max Range: 1.6548. Min Range: -1.6548

Max Act: 1.0494. Min Act: -0.0000

Data Index: 140429 (The Pile)

Max Activating Token Index: 910

Text #12

Max Range: 1.6548. Min Range: -1.6548

Max Act: 1.2533. Min Act: -0.0000

Data Index: 1309715 (The Pile)

Max Activating Token Index: 601

Text #13

Max Range: 1.6548. Min Range: -1.6548

Max Act: 1.1070. Min Act: -0.0000

Data Index: 1467937 (The Pile)

Max Activating Token Index: 120

Text #14

Max Range: 1.6548. Min Range: -1.6548

Max Act: 1.1716. Min Act: -0.0000

Data Index: 1819520 (The Pile)

Max Activating Token Index: 626

Text #15

Max Range: 1.6548. Min Range: -1.6548

Max Act: 1.1318. Min Act: -0.0000

Data Index: 359555 (The Pile)

Max Activating Token Index: 366

Text #16

Max Range: 1.6548. Min Range: -1.6548

Max Act: 1.1205. Min Act: -0.0000

Data Index: 308990 (The Pile)

Max Activating Token Index: 571

Text #17

Max Range: 1.6548. Min Range: -1.6548

Max Act: 1.1047. Min Act: -0.0000

Data Index: 736448 (The Pile)

Max Activating Token Index: 123

Text #18

Max Range: 1.6548. Min Range: -1.6548

Max Act: 1.0003. Min Act: -0.0000

Data Index: 458075 (The Pile)

Max Activating Token Index: 282

Text #19

Max Range: 1.6548. Min Range: -1.6548

Max Act: 0.8630. Min Act: -0.0000

Data Index: 77304 (The Pile)

Max Activating Token Index: 790