Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 276 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 5.9209. Min Range: -5.9209

Max Act: 5.9209. Min Act: -0.0001

Data Index: 218870 (C4 (Web Text))

Max Activating Token Index: 573

Text #1

Max Range: 5.9209. Min Range: -5.9209

Max Act: 5.4034. Min Act: -0.0001

Data Index: 506620 (C4 (Web Text))

Max Activating Token Index: 502

Text #2

Max Range: 5.9209. Min Range: -5.9209

Max Act: 4.8596. Min Act: -0.0001

Data Index: 39523 (C4 (Web Text))

Max Activating Token Index: 728

Text #3

Max Range: 5.9209. Min Range: -5.9209

Max Act: 4.8361. Min Act: -0.0001

Data Index: 727000 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 5.9209. Min Range: -5.9209

Max Act: 4.7411. Min Act: -0.0001

Data Index: 723049 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 5.9209. Min Range: -5.9209

Max Act: 4.6827. Min Act: -0.0001

Data Index: 735219 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 5.9209. Min Range: -5.9209

Max Act: 4.7002. Min Act: -0.0001

Data Index: 1140265 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 5.9209. Min Range: -5.9209

Max Act: 4.6497. Min Act: -0.0001

Data Index: 35343 (C4 (Web Text))

Max Activating Token Index: 593

Text #8

Max Range: 5.9209. Min Range: -5.9209

Max Act: 4.6035. Min Act: -0.0001

Data Index: 201562 (C4 (Web Text))

Max Activating Token Index: 344

Text #9

Max Range: 5.9209. Min Range: -5.9209

Max Act: 4.3675. Min Act: -0.0001

Data Index: 413489 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 5.9209. Min Range: -5.9209

Max Act: 4.0143. Min Act: -0.0001

Data Index: 982809 (C4 (Web Text))

Max Activating Token Index: 766

Text #11

Max Range: 5.9209. Min Range: -5.9209

Max Act: 4.0052. Min Act: -0.0000

Data Index: 104978 (C4 (Web Text))

Max Activating Token Index: 538

Text #12

Max Range: 5.9209. Min Range: -5.9209

Max Act: 4.5048. Min Act: -0.0001

Data Index: 137597 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 5.9209. Min Range: -5.9209

Max Act: 4.2545. Min Act: -0.0000

Data Index: 1157556 (C4 (Web Text))

Max Activating Token Index: 26

Text #14

Max Range: 5.9209. Min Range: -5.9209

Max Act: 4.2204. Min Act: -0.0001

Data Index: 1254497 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 5.9209. Min Range: -5.9209

Max Act: 4.3819. Min Act: -0.0001

Data Index: 936935 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 5.9209. Min Range: -5.9209

Max Act: 4.1133. Min Act: -0.0000

Data Index: 1138798 (C4 (Web Text))

Max Activating Token Index: 341

Text #17

Max Range: 5.9209. Min Range: -5.9209

Max Act: 3.9312. Min Act: -0.0001

Data Index: 529928 (C4 (Web Text))

Max Activating Token Index: 319

Text #18

Max Range: 5.9209. Min Range: -5.9209

Max Act: 4.0270. Min Act: -0.0001

Data Index: 30531 (C4 (Web Text))

Max Activating Token Index: 964

Text #19

Max Range: 5.9209. Min Range: -5.9209

Max Act: 4.0086. Min Act: -0.0001

Data Index: 345957 (C4 (Web Text))

Max Activating Token Index: 657