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

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

Neuron 3650 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5978. Min Range: -1.5978

Max Act: 1.5978. Min Act: -0.0001

Data Index: 99109 (C4 (Web Text))

Max Activating Token Index: 411

Text #1

Max Range: 1.5978. Min Range: -1.5978

Max Act: 1.4522. Min Act: -0.0001

Data Index: 98045 (C4 (Web Text))

Max Activating Token Index: 758

Text #2

Max Range: 1.5978. Min Range: -1.5978

Max Act: 1.5277. Min Act: -0.0001

Data Index: 540575 (C4 (Web Text))

Max Activating Token Index: 287

Text #3

Max Range: 1.5978. Min Range: -1.5978

Max Act: 1.4649. Min Act: -0.0001

Data Index: 166768 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 1.5978. Min Range: -1.5978

Max Act: 1.5202. Min Act: -0.0001

Data Index: 262538 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 1.5978. Min Range: -1.5978

Max Act: 1.4440. Min Act: -0.0001

Data Index: 433766 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 1.5978. Min Range: -1.5978

Max Act: 1.3470. Min Act: -0.0001

Data Index: 1214086 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 1.5978. Min Range: -1.5978

Max Act: 1.3785. Min Act: -0.0001

Data Index: 904394 (C4 (Web Text))

Max Activating Token Index: 952

Text #8

Max Range: 1.5978. Min Range: -1.5978

Max Act: 1.3576. Min Act: -0.0001

Data Index: 362642 (C4 (Web Text))

Max Activating Token Index: 230

Text #9

Max Range: 1.5978. Min Range: -1.5978

Max Act: 1.3168. Min Act: -0.0001

Data Index: 558777 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 1.5978. Min Range: -1.5978

Max Act: 1.3502. Min Act: -0.0001

Data Index: 939313 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 1.5978. Min Range: -1.5978

Max Act: 1.3257. Min Act: -0.0001

Data Index: 982043 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 1.5978. Min Range: -1.5978

Max Act: 1.2791. Min Act: -0.0001

Data Index: 544600 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 1.5978. Min Range: -1.5978

Max Act: 1.2978. Min Act: -0.0001

Data Index: 1248494 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 1.5978. Min Range: -1.5978

Max Act: 1.2599. Min Act: -0.0001

Data Index: 677776 (C4 (Web Text))

Max Activating Token Index: 392

Text #15

Max Range: 1.5978. Min Range: -1.5978

Max Act: 1.3334. Min Act: -0.0001

Data Index: 710826 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 1.5978. Min Range: -1.5978

Max Act: 1.2927. Min Act: -0.0001

Data Index: 895183 (C4 (Web Text))

Max Activating Token Index: 433

Text #17

Max Range: 1.5978. Min Range: -1.5978

Max Act: 1.2855. Min Act: -0.0001

Data Index: 706183 (C4 (Web Text))

Max Activating Token Index: 572

Text #18

Max Range: 1.5978. Min Range: -1.5978

Max Act: 1.2764. Min Act: -0.0001

Data Index: 1232926 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 1.5978. Min Range: -1.5978

Max Act: 1.2384. Min Act: -0.0001

Data Index: 159195 (C4 (Web Text))

Max Activating Token Index: 121