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

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

Neuron 311 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9942. Min Range: -2.9942

Max Act: 2.9942. Min Act: -0.0000

Data Index: 238774 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 2.9942. Min Range: -2.9942

Max Act: 2.8564. Min Act: -0.0000

Data Index: 854326 (C4 (Web Text))

Max Activating Token Index: 823

Text #2

Max Range: 2.9942. Min Range: -2.9942

Max Act: 2.8316. Min Act: -0.0000

Data Index: 186216 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 2.9942. Min Range: -2.9942

Max Act: 2.7468. Min Act: -0.0000

Data Index: 119832 (C4 (Web Text))

Max Activating Token Index: 719

Text #4

Max Range: 2.9942. Min Range: -2.9942

Max Act: 2.4696. Min Act: -0.0000

Data Index: 898296 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 2.9942. Min Range: -2.9942

Max Act: 2.6127. Min Act: -0.0000

Data Index: 557081 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 2.9942. Min Range: -2.9942

Max Act: 2.5805. Min Act: -0.0000

Data Index: 1214693 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 2.9942. Min Range: -2.9942

Max Act: 2.5576. Min Act: -0.0000

Data Index: 1240491 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 2.9942. Min Range: -2.9942

Max Act: 2.5603. Min Act: -0.0000

Data Index: 106841 (C4 (Web Text))

Max Activating Token Index: 898

Text #9

Max Range: 2.9942. Min Range: -2.9942

Max Act: 2.6562. Min Act: -0.0000

Data Index: 591883 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 2.9942. Min Range: -2.9942

Max Act: 2.5175. Min Act: -0.0000

Data Index: 1213910 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 2.9942. Min Range: -2.9942

Max Act: 2.5193. Min Act: -0.0000

Data Index: 1335926 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 2.9942. Min Range: -2.9942

Max Act: 2.4932. Min Act: -0.0000

Data Index: 118039 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 2.9942. Min Range: -2.9942

Max Act: 2.6259. Min Act: -0.0000

Data Index: 1286427 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 2.9942. Min Range: -2.9942

Max Act: 2.6027. Min Act: -0.0000

Data Index: 714827 (C4 (Web Text))

Max Activating Token Index: 501

Text #15

Max Range: 2.9942. Min Range: -2.9942

Max Act: 2.4719. Min Act: -0.0000

Data Index: 11359 (C4 (Web Text))

Max Activating Token Index: 295

Text #16

Max Range: 2.9942. Min Range: -2.9942

Max Act: 2.5973. Min Act: -0.0000

Data Index: 100075 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 2.9942. Min Range: -2.9942

Max Act: 2.4641. Min Act: -0.0000

Data Index: 925188 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 2.9942. Min Range: -2.9942

Max Act: 2.5964. Min Act: -0.0000

Data Index: 123560 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 2.9942. Min Range: -2.9942

Max Act: 2.4655. Min Act: -0.0000

Data Index: 448944 (C4 (Web Text))

Max Activating Token Index: 832