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

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

Neuron 2356 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1388. Min Act: -0.0001

Data Index: 391291 (C4 (Web Text))

Max Activating Token Index: 765

Text #1

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1345. Min Act: -0.0001

Data Index: 456793 (C4 (Web Text))

Max Activating Token Index: 653

Text #2

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1230. Min Act: -0.0001

Data Index: 302800 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1340. Min Act: -0.0000

Data Index: 658042 (C4 (Web Text))

Max Activating Token Index: 439

Text #4

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1288. Min Act: -0.0001

Data Index: 42428 (C4 (Web Text))

Max Activating Token Index: 539

Text #5

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1315. Min Act: -0.0001

Data Index: 214218 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1237. Min Act: -0.0001

Data Index: 250132 (C4 (Web Text))

Max Activating Token Index: 488

Text #7

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1262. Min Act: -0.0001

Data Index: 1198036 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1181. Min Act: -0.0001

Data Index: 201124 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1253. Min Act: -0.0001

Data Index: 852654 (C4 (Web Text))

Max Activating Token Index: 318

Text #10

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1067. Min Act: -0.0000

Data Index: 1162179 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.1124. Min Act: -0.0000

Data Index: 1077095 (C4 (Web Text))

Max Activating Token Index: 846

Text #12

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0969. Min Act: -0.0000

Data Index: 254722 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0947. Min Act: -0.0000

Data Index: 1114838 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0952. Min Act: -0.0000

Data Index: 1240101 (C4 (Web Text))

Max Activating Token Index: 728

Text #15

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0897. Min Act: -0.0000

Data Index: 745936 (C4 (Web Text))

Max Activating Token Index: 925

Text #16

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0883. Min Act: -0.0000

Data Index: 1110198 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0845. Min Act: -0.0000

Data Index: 1007640 (C4 (Web Text))

Max Activating Token Index: 99

Text #18

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0859. Min Act: -0.0000

Data Index: 991101 (C4 (Web Text))

Max Activating Token Index: 811

Text #19

Max Range: 0.1388. Min Range: -0.1388

Max Act: 0.0809. Min Act: -0.0000

Data Index: 1075566 (C4 (Web Text))

Max Activating Token Index: 795