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

Dataset: The Pile

Neuron 4299 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.4011. Min Act: -0.0000

Data Index: 499732 (The Pile)

Max Activating Token Index: 393

Text #1

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.4494. Min Act: -0.0000

Data Index: 1375409 (The Pile)

Max Activating Token Index: 429

Text #2

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.4330. Min Act: -0.0000

Data Index: 858309 (The Pile)

Max Activating Token Index: 933

Text #3

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.4154. Min Act: -0.0000

Data Index: 365074 (The Pile)

Max Activating Token Index: 369

Text #4

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3541. Min Act: -0.0000

Data Index: 563577 (The Pile)

Max Activating Token Index: 176

Text #5

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.4055. Min Act: -0.0000

Data Index: 1628116 (The Pile)

Max Activating Token Index: 60

Text #6

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3824. Min Act: -0.0000

Data Index: 462642 (The Pile)

Max Activating Token Index: 324

Text #7

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.4053. Min Act: -0.0000

Data Index: 1736833 (The Pile)

Max Activating Token Index: 540

Text #8

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3688. Min Act: -0.0000

Data Index: 1286262 (The Pile)

Max Activating Token Index: 652

Text #9

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3528. Min Act: -0.0000

Data Index: 1557037 (The Pile)

Max Activating Token Index: 1006

Text #10

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3580. Min Act: -0.0000

Data Index: 482044 (The Pile)

Max Activating Token Index: 124

Text #11

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3273. Min Act: -0.0000

Data Index: 1724376 (The Pile)

Max Activating Token Index: 194

Text #12

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3375. Min Act: -0.0000

Data Index: 1665020 (The Pile)

Max Activating Token Index: 634

Text #13

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3611. Min Act: -0.0000

Data Index: 1006836 (The Pile)

Max Activating Token Index: 11

Text #14

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3647. Min Act: -0.0000

Data Index: 927330 (The Pile)

Max Activating Token Index: 567

Text #15

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3255. Min Act: -0.0000

Data Index: 588980 (The Pile)

Max Activating Token Index: 394

Text #16

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3416. Min Act: -0.0000

Data Index: 845652 (The Pile)

Max Activating Token Index: 56

Text #17

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3396. Min Act: -0.0000

Data Index: 1942670 (The Pile)

Max Activating Token Index: 90

Text #18

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3494. Min Act: -0.0000

Data Index: 1294044 (The Pile)

Max Activating Token Index: 173

Text #19

Max Range: 0.4494. Min Range: -0.4494

Max Act: 0.3615. Min Act: -0.0000

Data Index: 1355681 (The Pile)

Max Activating Token Index: 573