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

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

Neuron 1984 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0167. Min Range: -1.0167

Max Act: 1.0167. Min Act: -0.0001

Data Index: 1035041 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 1.0167. Min Range: -1.0167

Max Act: 1.0107. Min Act: -0.0001

Data Index: 467962 (C4 (Web Text))

Max Activating Token Index: 923

Text #2

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.9926. Min Act: -0.0001

Data Index: 155087 (C4 (Web Text))

Max Activating Token Index: 480

Text #3

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.9357. Min Act: -0.0002

Data Index: 1097887 (C4 (Web Text))

Max Activating Token Index: 634

Text #4

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.9588. Min Act: -0.0002

Data Index: 166378 (C4 (Web Text))

Max Activating Token Index: 306

Text #5

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.9084. Min Act: -0.0002

Data Index: 964119 (C4 (Web Text))

Max Activating Token Index: 605

Text #6

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.9282. Min Act: -0.0002

Data Index: 841215 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.9298. Min Act: -0.0002

Data Index: 732766 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.9478. Min Act: -0.0002

Data Index: 396320 (C4 (Web Text))

Max Activating Token Index: 669

Text #9

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.9196. Min Act: -0.0002

Data Index: 842519 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.9214. Min Act: -0.0002

Data Index: 196703 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.8855. Min Act: -0.0002

Data Index: 477502 (C4 (Web Text))

Max Activating Token Index: 6

Text #12

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.8711. Min Act: -0.0002

Data Index: 1032135 (C4 (Web Text))

Max Activating Token Index: 444

Text #13

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.8952. Min Act: -0.0001

Data Index: 1241090 (C4 (Web Text))

Max Activating Token Index: 176

Text #14

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.8771. Min Act: -0.0002

Data Index: 1278355 (C4 (Web Text))

Max Activating Token Index: 967

Text #15

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.8739. Min Act: -0.0001

Data Index: 510557 (C4 (Web Text))

Max Activating Token Index: 425

Text #16

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.8669. Min Act: -0.0002

Data Index: 905263 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.7833. Min Act: -0.0002

Data Index: 991757 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.8445. Min Act: -0.0002

Data Index: 1209204 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 1.0167. Min Range: -1.0167

Max Act: 0.8507. Min Act: -0.0002

Data Index: 1005222 (C4 (Web Text))

Max Activating Token Index: 78