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

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

Neuron 1542 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3484. Min Act: -0.0001

Data Index: 1045014 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.4089. Min Act: -0.0001

Data Index: 335687 (C4 (Web Text))

Max Activating Token Index: 767

Text #2

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3099. Min Act: -0.0001

Data Index: 169247 (C4 (Web Text))

Max Activating Token Index: 775

Text #3

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3596. Min Act: -0.0001

Data Index: 437115 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3335. Min Act: -0.0001

Data Index: 575286 (C4 (Web Text))

Max Activating Token Index: 939

Text #5

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2910. Min Act: -0.0001

Data Index: 730079 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3273. Min Act: -0.0001

Data Index: 811966 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3260. Min Act: -0.0001

Data Index: 347793 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3595. Min Act: -0.0001

Data Index: 445614 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3182. Min Act: -0.0001

Data Index: 1095624 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3524. Min Act: -0.0001

Data Index: 1327997 (C4 (Web Text))

Max Activating Token Index: 895

Text #11

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3005. Min Act: -0.0001

Data Index: 321416 (C4 (Web Text))

Max Activating Token Index: 801

Text #12

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3153. Min Act: -0.0001

Data Index: 913870 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3364. Min Act: -0.0001

Data Index: 954053 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3202. Min Act: -0.0001

Data Index: 1141475 (C4 (Web Text))

Max Activating Token Index: 710

Text #15

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2834. Min Act: -0.0001

Data Index: 1298641 (C4 (Web Text))

Max Activating Token Index: 608

Text #16

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3152. Min Act: -0.0001

Data Index: 63152 (C4 (Web Text))

Max Activating Token Index: 312

Text #17

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3344. Min Act: -0.0001

Data Index: 417026 (C4 (Web Text))

Max Activating Token Index: 821

Text #18

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3244. Min Act: -0.0001

Data Index: 905569 (C4 (Web Text))

Max Activating Token Index: 618

Text #19

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2916. Min Act: -0.0001

Data Index: 1234366 (C4 (Web Text))

Max Activating Token Index: 547