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

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

Neuron 5374 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2115. Min Range: -1.2115

Max Act: 1.2021. Min Act: -0.0001

Data Index: 878415 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 1.2115. Min Range: -1.2115

Max Act: 1.2115. Min Act: -0.0001

Data Index: 982217 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 1.2115. Min Range: -1.2115

Max Act: 1.1939. Min Act: -0.0001

Data Index: 136358 (C4 (Web Text))

Max Activating Token Index: 493

Text #3

Max Range: 1.2115. Min Range: -1.2115

Max Act: 1.1312. Min Act: -0.0000

Data Index: 218871 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 1.2115. Min Range: -1.2115

Max Act: 1.1272. Min Act: -0.0000

Data Index: 60779 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 1.2115. Min Range: -1.2115

Max Act: 1.0328. Min Act: -0.0001

Data Index: 719071 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 1.2115. Min Range: -1.2115

Max Act: 1.0161. Min Act: -0.0001

Data Index: 1311256 (C4 (Web Text))

Max Activating Token Index: 561

Text #7

Max Range: 1.2115. Min Range: -1.2115

Max Act: 1.0203. Min Act: -0.0000

Data Index: 1183064 (C4 (Web Text))

Max Activating Token Index: 200

Text #8

Max Range: 1.2115. Min Range: -1.2115

Max Act: 1.0456. Min Act: -0.0000

Data Index: 492140 (C4 (Web Text))

Max Activating Token Index: 737

Text #9

Max Range: 1.2115. Min Range: -1.2115

Max Act: 0.9725. Min Act: -0.0001

Data Index: 182374 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 1.2115. Min Range: -1.2115

Max Act: 1.0024. Min Act: -0.0001

Data Index: 1187091 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 1.2115. Min Range: -1.2115

Max Act: 0.9955. Min Act: -0.0001

Data Index: 134891 (C4 (Web Text))

Max Activating Token Index: 644

Text #12

Max Range: 1.2115. Min Range: -1.2115

Max Act: 0.8899. Min Act: -0.0001

Data Index: 966514 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 1.2115. Min Range: -1.2115

Max Act: 0.9555. Min Act: -0.0000

Data Index: 195433 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 1.2115. Min Range: -1.2115

Max Act: 1.0168. Min Act: -0.0001

Data Index: 647446 (C4 (Web Text))

Max Activating Token Index: 535

Text #15

Max Range: 1.2115. Min Range: -1.2115

Max Act: 0.9653. Min Act: -0.0001

Data Index: 38729 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 1.2115. Min Range: -1.2115

Max Act: 0.9558. Min Act: -0.0001

Data Index: 196841 (C4 (Web Text))

Max Activating Token Index: 603

Text #17

Max Range: 1.2115. Min Range: -1.2115

Max Act: 0.8629. Min Act: -0.0001

Data Index: 826791 (C4 (Web Text))

Max Activating Token Index: 338

Text #18

Max Range: 1.2115. Min Range: -1.2115

Max Act: 0.9761. Min Act: -0.0001

Data Index: 308878 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 1.2115. Min Range: -1.2115

Max Act: 0.9428. Min Act: -0.0001

Data Index: 344350 (C4 (Web Text))

Max Activating Token Index: 511