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

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

Neuron 2917 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6388. Min Range: -1.6388

Max Act: 1.6388. Min Act: -0.0001

Data Index: 468495 (C4 (Web Text))

Max Activating Token Index: 70

Text #1

Max Range: 1.6388. Min Range: -1.6388

Max Act: 1.5935. Min Act: -0.0001

Data Index: 736252 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 1.6388. Min Range: -1.6388

Max Act: 1.5476. Min Act: -0.0001

Data Index: 599524 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 1.6388. Min Range: -1.6388

Max Act: 1.3755. Min Act: -0.0001

Data Index: 229007 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 1.6388. Min Range: -1.6388

Max Act: 1.5050. Min Act: -0.0001

Data Index: 1157579 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 1.6388. Min Range: -1.6388

Max Act: 1.3162. Min Act: -0.0001

Data Index: 1080711 (C4 (Web Text))

Max Activating Token Index: 154

Text #6

Max Range: 1.6388. Min Range: -1.6388

Max Act: 1.5220. Min Act: -0.0001

Data Index: 725984 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 1.6388. Min Range: -1.6388

Max Act: 1.5170. Min Act: -0.0001

Data Index: 836504 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 1.6388. Min Range: -1.6388

Max Act: 1.4777. Min Act: -0.0001

Data Index: 87390 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 1.6388. Min Range: -1.6388

Max Act: 1.5484. Min Act: -0.0001

Data Index: 487399 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 1.6388. Min Range: -1.6388

Max Act: 1.4975. Min Act: -0.0001

Data Index: 806070 (C4 (Web Text))

Max Activating Token Index: 345

Text #11

Max Range: 1.6388. Min Range: -1.6388

Max Act: 1.5344. Min Act: -0.0001

Data Index: 835290 (C4 (Web Text))

Max Activating Token Index: 339

Text #12

Max Range: 1.6388. Min Range: -1.6388

Max Act: 1.4968. Min Act: -0.0001

Data Index: 307025 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 1.6388. Min Range: -1.6388

Max Act: 1.3667. Min Act: -0.0001

Data Index: 1338776 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 1.6388. Min Range: -1.6388

Max Act: 1.4129. Min Act: -0.0001

Data Index: 1079473 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 1.6388. Min Range: -1.6388

Max Act: 1.4097. Min Act: -0.0001

Data Index: 112904 (C4 (Web Text))

Max Activating Token Index: 224

Text #16

Max Range: 1.6388. Min Range: -1.6388

Max Act: 1.5319. Min Act: -0.0001

Data Index: 1193850 (C4 (Web Text))

Max Activating Token Index: 370

Text #17

Max Range: 1.6388. Min Range: -1.6388

Max Act: 1.2950. Min Act: -0.0001

Data Index: 1043107 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 1.6388. Min Range: -1.6388

Max Act: 1.3566. Min Act: -0.0001

Data Index: 650823 (C4 (Web Text))

Max Activating Token Index: 491

Text #19

Max Range: 1.6388. Min Range: -1.6388

Max Act: 1.3921. Min Act: -0.0001

Data Index: 352172 (C4 (Web Text))

Max Activating Token Index: 276