Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 799 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4732. Min Range: -0.4732

Max Act: 0.4732. Min Act: -0.0001

Data Index: 1489014 (Python Code)

Max Activating Token Index: 441

Text #1

Max Range: 0.4732. Min Range: -0.4732

Max Act: 0.4438. Min Act: -0.0001

Data Index: 1600992 (Python Code)

Max Activating Token Index: 5

Text #2

Max Range: 0.4732. Min Range: -0.4732

Max Act: 0.4257. Min Act: -0.0001

Data Index: 1624963 (Python Code)

Max Activating Token Index: 18

Text #3

Max Range: 0.4732. Min Range: -0.4732

Max Act: 0.4294. Min Act: -0.0001

Data Index: 1514060 (Python Code)

Max Activating Token Index: 10

Text #4

Max Range: 0.4732. Min Range: -0.4732

Max Act: 0.4217. Min Act: -0.0002

Data Index: 1107201 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 0.4732. Min Range: -0.4732

Max Act: 0.4033. Min Act: -0.0002

Data Index: 1289998 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 0.4732. Min Range: -0.4732

Max Act: 0.4134. Min Act: -0.0002

Data Index: 1167782 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 0.4732. Min Range: -0.4732

Max Act: 0.3943. Min Act: -0.0001

Data Index: 1058259 (C4 (Web Text))

Max Activating Token Index: 476

Text #8

Max Range: 0.4732. Min Range: -0.4732

Max Act: 0.3923. Min Act: -0.0001

Data Index: 1219393 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 0.4732. Min Range: -0.4732

Max Act: 0.4200. Min Act: -0.0001

Data Index: 1554563 (Python Code)

Max Activating Token Index: 328

Text #10

Max Range: 0.4732. Min Range: -0.4732

Max Act: 0.4233. Min Act: -0.0002

Data Index: 1333697 (C4 (Web Text))

Max Activating Token Index: 148

Text #11

Max Range: 0.4732. Min Range: -0.4732

Max Act: 0.4032. Min Act: -0.0002

Data Index: 1206851 (C4 (Web Text))

Max Activating Token Index: 348

Text #12

Max Range: 0.4732. Min Range: -0.4732

Max Act: 0.3889. Min Act: -0.0002

Data Index: 972289 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 0.4732. Min Range: -0.4732

Max Act: 0.4190. Min Act: -0.0001

Data Index: 1070777 (C4 (Web Text))

Max Activating Token Index: 332

Text #14

Max Range: 0.4732. Min Range: -0.4732

Max Act: 0.4184. Min Act: -0.0001

Data Index: 1558036 (Python Code)

Max Activating Token Index: 49

Text #15

Max Range: 0.4732. Min Range: -0.4732

Max Act: 0.3869. Min Act: -0.0001

Data Index: 614911 (C4 (Web Text))

Max Activating Token Index: 97

Text #16

Max Range: 0.4732. Min Range: -0.4732

Max Act: 0.4122. Min Act: -0.0001

Data Index: 814841 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 0.4732. Min Range: -0.4732

Max Act: 0.4103. Min Act: -0.0002

Data Index: 650720 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 0.4732. Min Range: -0.4732

Max Act: 0.4274. Min Act: -0.0001

Data Index: 589587 (C4 (Web Text))

Max Activating Token Index: 767

Text #19

Max Range: 0.4732. Min Range: -0.4732

Max Act: 0.3690. Min Act: -0.0001

Data Index: 1598507 (Python Code)

Max Activating Token Index: 107