Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 766 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.6366. Min Act: -0.0001

Data Index: 1315875 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.5866. Min Act: -0.0001

Data Index: 151868 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.5852. Min Act: -0.0001

Data Index: 639926 (C4 (Web Text))

Max Activating Token Index: 153

Text #3

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.5662. Min Act: -0.0001

Data Index: 612457 (C4 (Web Text))

Max Activating Token Index: 302

Text #4

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.6174. Min Act: -0.0001

Data Index: 613512 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.5907. Min Act: -0.0001

Data Index: 1141366 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.5921. Min Act: -0.0001

Data Index: 391367 (C4 (Web Text))

Max Activating Token Index: 211

Text #7

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.5508. Min Act: -0.0001

Data Index: 754465 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.5550. Min Act: -0.0001

Data Index: 161035 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.5382. Min Act: -0.0001

Data Index: 535055 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.5353. Min Act: -0.0001

Data Index: 1044232 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.5713. Min Act: -0.0001

Data Index: 950423 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.5486. Min Act: -0.0001

Data Index: 608598 (C4 (Web Text))

Max Activating Token Index: 157

Text #13

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.5083. Min Act: -0.0001

Data Index: 1230625 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.5414. Min Act: -0.0001

Data Index: 856857 (C4 (Web Text))

Max Activating Token Index: 909

Text #15

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.5134. Min Act: -0.0001

Data Index: 656660 (C4 (Web Text))

Max Activating Token Index: 983

Text #16

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.5388. Min Act: -0.0001

Data Index: 1088740 (C4 (Web Text))

Max Activating Token Index: 604

Text #17

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.5289. Min Act: -0.0001

Data Index: 1123592 (C4 (Web Text))

Max Activating Token Index: 442

Text #18

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.5267. Min Act: -0.0001

Data Index: 1081460 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 0.6366. Min Range: -0.6366

Max Act: 0.5258. Min Act: -0.0001

Data Index: 788859 (C4 (Web Text))

Max Activating Token Index: 60