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

Dataset: The Pile

Neuron 2681 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: 1.4042. Min Range: -1.4042

Max Act: 1.3292. Min Act: -0.0000

Data Index: 815434 (The Pile)

Max Activating Token Index: 131

Text #1

Max Range: 1.4042. Min Range: -1.4042

Max Act: 1.4042. Min Act: -0.0000

Data Index: 13889 (The Pile)

Max Activating Token Index: 485

Text #2

Max Range: 1.4042. Min Range: -1.4042

Max Act: 1.1882. Min Act: -0.0000

Data Index: 53250 (The Pile)

Max Activating Token Index: 32

Text #3

Max Range: 1.4042. Min Range: -1.4042

Max Act: 1.1432. Min Act: -0.0000

Data Index: 1023168 (The Pile)

Max Activating Token Index: 830

Text #4

Max Range: 1.4042. Min Range: -1.4042

Max Act: 1.0933. Min Act: -0.0000

Data Index: 186718 (The Pile)

Max Activating Token Index: 179

Text #5

Max Range: 1.4042. Min Range: -1.4042

Max Act: 1.0382. Min Act: -0.0000

Data Index: 1937551 (The Pile)

Max Activating Token Index: 212

Text #6

Max Range: 1.4042. Min Range: -1.4042

Max Act: 1.0855. Min Act: -0.0000

Data Index: 1624954 (The Pile)

Max Activating Token Index: 118

Text #7

Max Range: 1.4042. Min Range: -1.4042

Max Act: 1.0034. Min Act: -0.0000

Data Index: 1380473 (The Pile)

Max Activating Token Index: 978

Text #8

Max Range: 1.4042. Min Range: -1.4042

Max Act: 0.9346. Min Act: -0.0000

Data Index: 1245684 (The Pile)

Max Activating Token Index: 998

Text #9

Max Range: 1.4042. Min Range: -1.4042

Max Act: 1.0422. Min Act: -0.0000

Data Index: 573844 (The Pile)

Max Activating Token Index: 370

Text #10

Max Range: 1.4042. Min Range: -1.4042

Max Act: 0.9983. Min Act: -0.0000

Data Index: 901810 (The Pile)

Max Activating Token Index: 939

Text #11

Max Range: 1.4042. Min Range: -1.4042

Max Act: 0.8716. Min Act: -0.0000

Data Index: 515633 (The Pile)

Max Activating Token Index: 971

Text #12

Max Range: 1.4042. Min Range: -1.4042

Max Act: 0.6909. Min Act: -0.0000

Data Index: 1657555 (The Pile)

Max Activating Token Index: 16

Text #13

Max Range: 1.4042. Min Range: -1.4042

Max Act: 0.9074. Min Act: -0.0000

Data Index: 311726 (The Pile)

Max Activating Token Index: 224

Text #14

Max Range: 1.4042. Min Range: -1.4042

Max Act: 1.0842. Min Act: -0.0000

Data Index: 1611429 (The Pile)

Max Activating Token Index: 998

Text #15

Max Range: 1.4042. Min Range: -1.4042

Max Act: 1.0188. Min Act: -0.0000

Data Index: 112968 (The Pile)

Max Activating Token Index: 201

Text #16

Max Range: 1.4042. Min Range: -1.4042

Max Act: 0.8974. Min Act: -0.0000

Data Index: 1625875 (The Pile)

Max Activating Token Index: 265

Text #17

Max Range: 1.4042. Min Range: -1.4042

Max Act: 0.8583. Min Act: -0.0000

Data Index: 1758518 (The Pile)

Max Activating Token Index: 1019

Text #18

Max Range: 1.4042. Min Range: -1.4042

Max Act: 0.9375. Min Act: -0.0000

Data Index: 1114143 (The Pile)

Max Activating Token Index: 362

Text #19

Max Range: 1.4042. Min Range: -1.4042

Max Act: 0.9876. Min Act: -0.0000

Data Index: 733367 (The Pile)

Max Activating Token Index: 202