Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3704 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1373. Min Range: -1.1373

Max Act: 1.1373. Min Act: -0.0000

Data Index: 1015589 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 1.1373. Min Range: -1.1373

Max Act: 0.9979. Min Act: -0.0000

Data Index: 113548 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 1.1373. Min Range: -1.1373

Max Act: 0.9691. Min Act: -0.0000

Data Index: 646230 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 1.1373. Min Range: -1.1373

Max Act: 0.8805. Min Act: -0.0000

Data Index: 109926 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 1.1373. Min Range: -1.1373

Max Act: 0.9255. Min Act: -0.0000

Data Index: 656546 (C4 (Web Text))

Max Activating Token Index: 565

Text #5

Max Range: 1.1373. Min Range: -1.1373

Max Act: 0.9774. Min Act: -0.0000

Data Index: 649029 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 1.1373. Min Range: -1.1373

Max Act: 0.9768. Min Act: -0.0000

Data Index: 1092536 (C4 (Web Text))

Max Activating Token Index: 670

Text #7

Max Range: 1.1373. Min Range: -1.1373

Max Act: 0.8906. Min Act: -0.0001

Data Index: 337616 (C4 (Web Text))

Max Activating Token Index: 972

Text #8

Max Range: 1.1373. Min Range: -1.1373

Max Act: 0.8921. Min Act: -0.0000

Data Index: 611424 (C4 (Web Text))

Max Activating Token Index: 127

Text #9

Max Range: 1.1373. Min Range: -1.1373

Max Act: 0.9238. Min Act: -0.0000

Data Index: 167114 (C4 (Web Text))

Max Activating Token Index: 632

Text #10

Max Range: 1.1373. Min Range: -1.1373

Max Act: 0.8975. Min Act: -0.0000

Data Index: 214475 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 1.1373. Min Range: -1.1373

Max Act: 0.8330. Min Act: -0.0000

Data Index: 126273 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 1.1373. Min Range: -1.1373

Max Act: 0.9027. Min Act: -0.0000

Data Index: 1189365 (C4 (Web Text))

Max Activating Token Index: 408

Text #13

Max Range: 1.1373. Min Range: -1.1373

Max Act: 0.9026. Min Act: -0.0001

Data Index: 526227 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 1.1373. Min Range: -1.1373

Max Act: 0.8470. Min Act: -0.0000

Data Index: 90340 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 1.1373. Min Range: -1.1373

Max Act: 0.9146. Min Act: -0.0000

Data Index: 703474 (C4 (Web Text))

Max Activating Token Index: 674

Text #16

Max Range: 1.1373. Min Range: -1.1373

Max Act: 0.8626. Min Act: -0.0000

Data Index: 770837 (C4 (Web Text))

Max Activating Token Index: 896

Text #17

Max Range: 1.1373. Min Range: -1.1373

Max Act: 0.8594. Min Act: -0.0000

Data Index: 1195197 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 1.1373. Min Range: -1.1373

Max Act: 0.8313. Min Act: -0.0000

Data Index: 1236032 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 1.1373. Min Range: -1.1373

Max Act: 0.8126. Min Act: -0.0000

Data Index: 776400 (C4 (Web Text))

Max Activating Token Index: 153