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

Dataset: The Pile

Neuron 2333 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8946. Min Range: -1.8946

Max Act: 1.8946. Min Act: -0.0000

Data Index: 279305 (The Pile)

Max Activating Token Index: 786

Text #1

Max Range: 1.8946. Min Range: -1.8946

Max Act: 1.7610. Min Act: -0.0000

Data Index: 1080585 (The Pile)

Max Activating Token Index: 33

Text #2

Max Range: 1.8946. Min Range: -1.8946

Max Act: 1.6333. Min Act: -0.0000

Data Index: 1001949 (The Pile)

Max Activating Token Index: 135

Text #3

Max Range: 1.8946. Min Range: -1.8946

Max Act: 1.4367. Min Act: -0.0000

Data Index: 1530065 (The Pile)

Max Activating Token Index: 544

Text #4

Max Range: 1.8946. Min Range: -1.8946

Max Act: 1.5385. Min Act: -0.0000

Data Index: 1701593 (The Pile)

Max Activating Token Index: 671

Text #5

Max Range: 1.8946. Min Range: -1.8946

Max Act: 1.3775. Min Act: -0.0000

Data Index: 1489844 (The Pile)

Max Activating Token Index: 189

Text #6

Max Range: 1.8946. Min Range: -1.8946

Max Act: 1.4132. Min Act: -0.0000

Data Index: 1702955 (The Pile)

Max Activating Token Index: 325

Text #7

Max Range: 1.8946. Min Range: -1.8946

Max Act: 1.2639. Min Act: -0.0000

Data Index: 1835257 (The Pile)

Max Activating Token Index: 581

Text #8

Max Range: 1.8946. Min Range: -1.8946

Max Act: 1.3475. Min Act: -0.0000

Data Index: 387462 (The Pile)

Max Activating Token Index: 74

Text #9

Max Range: 1.8946. Min Range: -1.8946

Max Act: 1.2162. Min Act: -0.0000

Data Index: 1495450 (The Pile)

Max Activating Token Index: 644

Text #10

Max Range: 1.8946. Min Range: -1.8946

Max Act: 1.2803. Min Act: -0.0000

Data Index: 1513063 (The Pile)

Max Activating Token Index: 558

Text #11

Max Range: 1.8946. Min Range: -1.8946

Max Act: 1.3132. Min Act: -0.0000

Data Index: 767813 (The Pile)

Max Activating Token Index: 79

Text #12

Max Range: 1.8946. Min Range: -1.8946

Max Act: 1.3489. Min Act: -0.0000

Data Index: 1051030 (The Pile)

Max Activating Token Index: 899

Text #13

Max Range: 1.8946. Min Range: -1.8946

Max Act: 1.2213. Min Act: -0.0000

Data Index: 1467385 (The Pile)

Max Activating Token Index: 598

Text #14

Max Range: 1.8946. Min Range: -1.8946

Max Act: 1.2540. Min Act: -0.0000

Data Index: 851424 (The Pile)

Max Activating Token Index: 1006

Text #15

Max Range: 1.8946. Min Range: -1.8946

Max Act: 1.2157. Min Act: -0.0000

Data Index: 576294 (The Pile)

Max Activating Token Index: 269

Text #16

Max Range: 1.8946. Min Range: -1.8946

Max Act: 1.2078. Min Act: -0.0000

Data Index: 534887 (The Pile)

Max Activating Token Index: 741

Text #17

Max Range: 1.8946. Min Range: -1.8946

Max Act: 1.1348. Min Act: -0.0000

Data Index: 1262454 (The Pile)

Max Activating Token Index: 681

Text #18

Max Range: 1.8946. Min Range: -1.8946

Max Act: 1.1709. Min Act: -0.0000

Data Index: 528065 (The Pile)

Max Activating Token Index: 898

Text #19

Max Range: 1.8946. Min Range: -1.8946

Max Act: 1.2369. Min Act: -0.0000

Data Index: 1819429 (The Pile)

Max Activating Token Index: 70