Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2440 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.6997. Min Act: -0.0001

Data Index: 702944 (C4 (Web Text))

Max Activating Token Index: 1016

Text #1

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.6329. Min Act: -0.0001

Data Index: 1542462 (Python Code)

Max Activating Token Index: 55

Text #2

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.5901. Min Act: -0.0001

Data Index: 1400112 (Python Code)

Max Activating Token Index: 273

Text #3

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.6302. Min Act: -0.0001

Data Index: 1365107 (Python Code)

Max Activating Token Index: 267

Text #4

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.5844. Min Act: -0.0001

Data Index: 533980 (C4 (Web Text))

Max Activating Token Index: 318

Text #5

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.5698. Min Act: -0.0001

Data Index: 1257983 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.5269. Min Act: -0.0001

Data Index: 114936 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.5737. Min Act: -0.0001

Data Index: 1304699 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.4736. Min Act: -0.0001

Data Index: 1080223 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.5297. Min Act: -0.0001

Data Index: 189252 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.5930. Min Act: -0.0001

Data Index: 1635937 (Python Code)

Max Activating Token Index: 423

Text #11

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.5508. Min Act: -0.0001

Data Index: 231681 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.5285. Min Act: -0.0001

Data Index: 632077 (C4 (Web Text))

Max Activating Token Index: 201

Text #13

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.5123. Min Act: -0.0001

Data Index: 164142 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.4577. Min Act: -0.0001

Data Index: 330205 (C4 (Web Text))

Max Activating Token Index: 690

Text #15

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.4873. Min Act: -0.0001

Data Index: 535562 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.5041. Min Act: -0.0001

Data Index: 393923 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.4885. Min Act: -0.0001

Data Index: 1134729 (C4 (Web Text))

Max Activating Token Index: 788

Text #18

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.4988. Min Act: -0.0001

Data Index: 448795 (C4 (Web Text))

Max Activating Token Index: 225

Text #19

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.4787. Min Act: -0.0001

Data Index: 133374 (C4 (Web Text))

Max Activating Token Index: 899