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

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

Neuron 3696 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: 0.7074. Min Range: -0.7074

Max Act: 0.7074. Min Act: -0.0000

Data Index: 1145375 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 0.7074. Min Range: -0.7074

Max Act: 0.5969. Min Act: -0.0000

Data Index: 986628 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 0.7074. Min Range: -0.7074

Max Act: 0.6149. Min Act: -0.0000

Data Index: 722416 (C4 (Web Text))

Max Activating Token Index: 159

Text #3

Max Range: 0.7074. Min Range: -0.7074

Max Act: 0.5942. Min Act: -0.0000

Data Index: 621219 (C4 (Web Text))

Max Activating Token Index: 477

Text #4

Max Range: 0.7074. Min Range: -0.7074

Max Act: 0.4900. Min Act: -0.0000

Data Index: 565404 (C4 (Web Text))

Max Activating Token Index: 161

Text #5

Max Range: 0.7074. Min Range: -0.7074

Max Act: 0.5532. Min Act: -0.0000

Data Index: 949759 (C4 (Web Text))

Max Activating Token Index: 191

Text #6

Max Range: 0.7074. Min Range: -0.7074

Max Act: 0.5307. Min Act: -0.0000

Data Index: 160649 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 0.7074. Min Range: -0.7074

Max Act: 0.5662. Min Act: -0.0000

Data Index: 829052 (C4 (Web Text))

Max Activating Token Index: 272

Text #8

Max Range: 0.7074. Min Range: -0.7074

Max Act: 0.5650. Min Act: -0.0000

Data Index: 32412 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 0.7074. Min Range: -0.7074

Max Act: 0.4846. Min Act: -0.0000

Data Index: 777833 (C4 (Web Text))

Max Activating Token Index: 846

Text #10

Max Range: 0.7074. Min Range: -0.7074

Max Act: 0.5175. Min Act: -0.0000

Data Index: 1315622 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 0.7074. Min Range: -0.7074

Max Act: 0.5007. Min Act: -0.0000

Data Index: 791493 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 0.7074. Min Range: -0.7074

Max Act: 0.4985. Min Act: -0.0000

Data Index: 878761 (C4 (Web Text))

Max Activating Token Index: 349

Text #13

Max Range: 0.7074. Min Range: -0.7074

Max Act: 0.5321. Min Act: -0.0000

Data Index: 1028458 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 0.7074. Min Range: -0.7074

Max Act: 0.5813. Min Act: -0.0000

Data Index: 360685 (C4 (Web Text))

Max Activating Token Index: 191

Text #15

Max Range: 0.7074. Min Range: -0.7074

Max Act: 0.5451. Min Act: -0.0000

Data Index: 1168038 (C4 (Web Text))

Max Activating Token Index: 466

Text #16

Max Range: 0.7074. Min Range: -0.7074

Max Act: 0.5668. Min Act: -0.0000

Data Index: 994359 (C4 (Web Text))

Max Activating Token Index: 688

Text #17

Max Range: 0.7074. Min Range: -0.7074

Max Act: 0.5238. Min Act: -0.0000

Data Index: 944852 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 0.7074. Min Range: -0.7074

Max Act: 0.4921. Min Act: -0.0000

Data Index: 897767 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 0.7074. Min Range: -0.7074

Max Act: 0.4708. Min Act: -0.0000

Data Index: 622545 (C4 (Web Text))

Max Activating Token Index: 332