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

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

Neuron 335 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.4866. Min Act: -0.0001

Data Index: 696942 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.4732. Min Act: -0.0001

Data Index: 693869 (C4 (Web Text))

Max Activating Token Index: 597

Text #2

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.4831. Min Act: -0.0001

Data Index: 1286930 (C4 (Web Text))

Max Activating Token Index: 422

Text #3

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.4588. Min Act: -0.0001

Data Index: 753897 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.4623. Min Act: -0.0001

Data Index: 499650 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.4473. Min Act: -0.0001

Data Index: 884810 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.4349. Min Act: -0.0001

Data Index: 281252 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.4403. Min Act: -0.0001

Data Index: 1183458 (C4 (Web Text))

Max Activating Token Index: 514

Text #8

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.4470. Min Act: -0.0001

Data Index: 344136 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.4325. Min Act: -0.0001

Data Index: 765418 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.4244. Min Act: -0.0001

Data Index: 523242 (C4 (Web Text))

Max Activating Token Index: 1022

Text #11

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.3910. Min Act: -0.0001

Data Index: 189860 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.4439. Min Act: -0.0001

Data Index: 1226447 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.4068. Min Act: -0.0001

Data Index: 1063080 (C4 (Web Text))

Max Activating Token Index: 58

Text #14

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.4214. Min Act: -0.0001

Data Index: 1230884 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.4195. Min Act: -0.0001

Data Index: 628936 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.3954. Min Act: -0.0001

Data Index: 931197 (C4 (Web Text))

Max Activating Token Index: 770

Text #17

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.3965. Min Act: -0.0001

Data Index: 679099 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.4069. Min Act: -0.0001

Data Index: 784730 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 0.4866. Min Range: -0.4866

Max Act: 0.4069. Min Act: -0.0001

Data Index: 963116 (C4 (Web Text))

Max Activating Token Index: 48