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

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

Neuron 4264 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7270. Min Range: -1.7270

Max Act: 1.7270. Min Act: -0.0000

Data Index: 615424 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 1.7270. Min Range: -1.7270

Max Act: 1.6792. Min Act: -0.0000

Data Index: 544034 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 1.7270. Min Range: -1.7270

Max Act: 1.4977. Min Act: -0.0000

Data Index: 905071 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 1.7270. Min Range: -1.7270

Max Act: 1.5435. Min Act: -0.0000

Data Index: 272612 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 1.7270. Min Range: -1.7270

Max Act: 1.4864. Min Act: -0.0000

Data Index: 1042913 (C4 (Web Text))

Max Activating Token Index: 781

Text #5

Max Range: 1.7270. Min Range: -1.7270

Max Act: 1.3292. Min Act: -0.0000

Data Index: 162246 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 1.7270. Min Range: -1.7270

Max Act: 1.1265. Min Act: -0.0000

Data Index: 379296 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 1.7270. Min Range: -1.7270

Max Act: 1.1835. Min Act: -0.0000

Data Index: 356876 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 1.7270. Min Range: -1.7270

Max Act: 1.1458. Min Act: -0.0000

Data Index: 17423 (C4 (Web Text))

Max Activating Token Index: 461

Text #9

Max Range: 1.7270. Min Range: -1.7270

Max Act: 1.0851. Min Act: -0.0000

Data Index: 679101 (C4 (Web Text))

Max Activating Token Index: 253

Text #10

Max Range: 1.7270. Min Range: -1.7270

Max Act: 1.1107. Min Act: -0.0000

Data Index: 798942 (C4 (Web Text))

Max Activating Token Index: 491

Text #11

Max Range: 1.7270. Min Range: -1.7270

Max Act: 1.1060. Min Act: -0.0000

Data Index: 36966 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 1.7270. Min Range: -1.7270

Max Act: 1.0999. Min Act: -0.0000

Data Index: 1163001 (C4 (Web Text))

Max Activating Token Index: 465

Text #13

Max Range: 1.7270. Min Range: -1.7270

Max Act: 1.0826. Min Act: -0.0000

Data Index: 288030 (C4 (Web Text))

Max Activating Token Index: 920

Text #14

Max Range: 1.7270. Min Range: -1.7270

Max Act: 1.0921. Min Act: -0.0000

Data Index: 627399 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 1.7270. Min Range: -1.7270

Max Act: 0.9925. Min Act: -0.0000

Data Index: 1051663 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 1.7270. Min Range: -1.7270

Max Act: 1.1171. Min Act: -0.0000

Data Index: 416814 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 1.7270. Min Range: -1.7270

Max Act: 1.0567. Min Act: -0.0000

Data Index: 411206 (C4 (Web Text))

Max Activating Token Index: 947

Text #18

Max Range: 1.7270. Min Range: -1.7270

Max Act: 0.9381. Min Act: -0.0000

Data Index: 472534 (C4 (Web Text))

Max Activating Token Index: 985

Text #19

Max Range: 1.7270. Min Range: -1.7270

Max Act: 1.0531. Min Act: -0.0000

Data Index: 344462 (C4 (Web Text))

Max Activating Token Index: 578