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

Dataset: The Pile

Neuron 4215 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: 0.3121. Min Range: -0.3121

Max Act: 0.3121. Min Act: -0.0000

Data Index: 414331 (The Pile)

Max Activating Token Index: 680

Text #1

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2891. Min Act: -0.0000

Data Index: 1307016 (The Pile)

Max Activating Token Index: 52

Text #2

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2750. Min Act: -0.0000

Data Index: 1427539 (The Pile)

Max Activating Token Index: 1006

Text #3

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2960. Min Act: -0.0000

Data Index: 1407387 (The Pile)

Max Activating Token Index: 274

Text #4

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2807. Min Act: -0.0000

Data Index: 1565022 (The Pile)

Max Activating Token Index: 100

Text #5

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2882. Min Act: -0.0000

Data Index: 1925158 (The Pile)

Max Activating Token Index: 98

Text #6

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2459. Min Act: -0.0000

Data Index: 1135148 (The Pile)

Max Activating Token Index: 225

Text #7

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2516. Min Act: -0.0000

Data Index: 1879148 (The Pile)

Max Activating Token Index: 117

Text #8

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2366. Min Act: -0.0000

Data Index: 850115 (The Pile)

Max Activating Token Index: 35

Text #9

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2222. Min Act: -0.0000

Data Index: 730709 (The Pile)

Max Activating Token Index: 75

Text #10

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2235. Min Act: -0.0000

Data Index: 350754 (The Pile)

Max Activating Token Index: 448

Text #11

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.1841. Min Act: -0.0000

Data Index: 1040996 (The Pile)

Max Activating Token Index: 935

Text #12

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2380. Min Act: -0.0000

Data Index: 1531441 (The Pile)

Max Activating Token Index: 1000

Text #13

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2297. Min Act: -0.0000

Data Index: 557900 (The Pile)

Max Activating Token Index: 124

Text #14

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2066. Min Act: -0.0000

Data Index: 1903464 (The Pile)

Max Activating Token Index: 786

Text #15

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2196. Min Act: -0.0000

Data Index: 357956 (The Pile)

Max Activating Token Index: 668

Text #16

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2055. Min Act: -0.0000

Data Index: 282536 (The Pile)

Max Activating Token Index: 480

Text #17

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2202. Min Act: -0.0000

Data Index: 1428380 (The Pile)

Max Activating Token Index: 295

Text #18

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2142. Min Act: -0.0000

Data Index: 1346913 (The Pile)

Max Activating Token Index: 868

Text #19

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2160. Min Act: -0.0000

Data Index: 659894 (The Pile)

Max Activating Token Index: 613