Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3475 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.4458. Min Act: -0.0001

Data Index: 852049 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.4508. Min Act: -0.0001

Data Index: 630782 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.4402. Min Act: -0.0001

Data Index: 1063881 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.4373. Min Act: -0.0001

Data Index: 676910 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.4294. Min Act: -0.0001

Data Index: 278527 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.4281. Min Act: -0.0001

Data Index: 699106 (C4 (Web Text))

Max Activating Token Index: 553

Text #6

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.4207. Min Act: -0.0001

Data Index: 993474 (C4 (Web Text))

Max Activating Token Index: 4

Text #7

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.4267. Min Act: -0.0001

Data Index: 801257 (C4 (Web Text))

Max Activating Token Index: 785

Text #8

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.4220. Min Act: -0.0001

Data Index: 936054 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.4160. Min Act: -0.0001

Data Index: 334123 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.4144. Min Act: -0.0001

Data Index: 498723 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.4108. Min Act: -0.0001

Data Index: 609294 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.4095. Min Act: -0.0001

Data Index: 1007476 (C4 (Web Text))

Max Activating Token Index: 613

Text #13

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.4086. Min Act: -0.0001

Data Index: 454729 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.4151. Min Act: -0.0001

Data Index: 680487 (C4 (Web Text))

Max Activating Token Index: 516

Text #15

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.4148. Min Act: -0.0001

Data Index: 350731 (C4 (Web Text))

Max Activating Token Index: 271

Text #16

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.4101. Min Act: -0.0001

Data Index: 1312639 (C4 (Web Text))

Max Activating Token Index: 774

Text #17

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.4205. Min Act: -0.0001

Data Index: 694262 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.4043. Min Act: -0.0001

Data Index: 304616 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.4153. Min Act: -0.0001

Data Index: 1167217 (C4 (Web Text))

Max Activating Token Index: 1023