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

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

Neuron 2034 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6466. Min Range: -0.6466

Max Act: 0.6466. Min Act: -0.0001

Data Index: 1159559 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 0.6466. Min Range: -0.6466

Max Act: 0.5512. Min Act: -0.0001

Data Index: 218894 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 0.6466. Min Range: -0.6466

Max Act: 0.5728. Min Act: -0.0001

Data Index: 223752 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 0.6466. Min Range: -0.6466

Max Act: 0.5248. Min Act: -0.0001

Data Index: 1256075 (C4 (Web Text))

Max Activating Token Index: 415

Text #4

Max Range: 0.6466. Min Range: -0.6466

Max Act: 0.4162. Min Act: -0.0001

Data Index: 772030 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 0.6466. Min Range: -0.6466

Max Act: 0.4458. Min Act: -0.0001

Data Index: 53723 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 0.6466. Min Range: -0.6466

Max Act: 0.4341. Min Act: -0.0001

Data Index: 537394 (C4 (Web Text))

Max Activating Token Index: 794

Text #7

Max Range: 0.6466. Min Range: -0.6466

Max Act: 0.4353. Min Act: -0.0001

Data Index: 1136030 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 0.6466. Min Range: -0.6466

Max Act: 0.4340. Min Act: -0.0001

Data Index: 1003550 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 0.6466. Min Range: -0.6466

Max Act: 0.4339. Min Act: -0.0001

Data Index: 792447 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 0.6466. Min Range: -0.6466

Max Act: 0.4418. Min Act: -0.0001

Data Index: 204672 (C4 (Web Text))

Max Activating Token Index: 430

Text #11

Max Range: 0.6466. Min Range: -0.6466

Max Act: 0.4287. Min Act: -0.0000

Data Index: 1171900 (C4 (Web Text))

Max Activating Token Index: 182

Text #12

Max Range: 0.6466. Min Range: -0.6466

Max Act: 0.3833. Min Act: -0.0001

Data Index: 570556 (C4 (Web Text))

Max Activating Token Index: 394

Text #13

Max Range: 0.6466. Min Range: -0.6466

Max Act: 0.4150. Min Act: -0.0001

Data Index: 481731 (C4 (Web Text))

Max Activating Token Index: 501

Text #14

Max Range: 0.6466. Min Range: -0.6466

Max Act: 0.3962. Min Act: -0.0001

Data Index: 698650 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 0.6466. Min Range: -0.6466

Max Act: 0.3966. Min Act: -0.0001

Data Index: 110472 (C4 (Web Text))

Max Activating Token Index: 1006

Text #16

Max Range: 0.6466. Min Range: -0.6466

Max Act: 0.4274. Min Act: -0.0000

Data Index: 478328 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 0.6466. Min Range: -0.6466

Max Act: 0.3887. Min Act: -0.0001

Data Index: 702893 (C4 (Web Text))

Max Activating Token Index: 282

Text #18

Max Range: 0.6466. Min Range: -0.6466

Max Act: 0.3869. Min Act: -0.0001

Data Index: 3635 (C4 (Web Text))

Max Activating Token Index: 853

Text #19

Max Range: 0.6466. Min Range: -0.6466

Max Act: 0.3826. Min Act: -0.0001

Data Index: 1051854 (C4 (Web Text))

Max Activating Token Index: 999