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

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

Neuron 3582 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: 3.2225. Min Range: -3.2225

Max Act: 2.3642. Min Act: -0.0000

Data Index: 1107876 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 3.2225. Min Range: -3.2225

Max Act: 3.2225. Min Act: -0.0000

Data Index: 1247352 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 3.2225. Min Range: -3.2225

Max Act: 3.1037. Min Act: -0.0000

Data Index: 859985 (C4 (Web Text))

Max Activating Token Index: 430

Text #3

Max Range: 3.2225. Min Range: -3.2225

Max Act: 3.0474. Min Act: -0.0001

Data Index: 413119 (C4 (Web Text))

Max Activating Token Index: 420

Text #4

Max Range: 3.2225. Min Range: -3.2225

Max Act: 3.1465. Min Act: -0.0000

Data Index: 140727 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 3.2225. Min Range: -3.2225

Max Act: 2.7893. Min Act: -0.0000

Data Index: 265916 (C4 (Web Text))

Max Activating Token Index: 469

Text #6

Max Range: 3.2225. Min Range: -3.2225

Max Act: 2.9509. Min Act: -0.0000

Data Index: 630388 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 3.2225. Min Range: -3.2225

Max Act: 2.8529. Min Act: -0.0001

Data Index: 883007 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 3.2225. Min Range: -3.2225

Max Act: 2.8909. Min Act: -0.0000

Data Index: 607896 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 3.2225. Min Range: -3.2225

Max Act: 2.7184. Min Act: -0.0000

Data Index: 534508 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 3.2225. Min Range: -3.2225

Max Act: 2.0818. Min Act: -0.0001

Data Index: 385973 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 3.2225. Min Range: -3.2225

Max Act: 2.5493. Min Act: -0.0000

Data Index: 730514 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 3.2225. Min Range: -3.2225

Max Act: 2.3956. Min Act: -0.0000

Data Index: 846548 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 3.2225. Min Range: -3.2225

Max Act: 2.4495. Min Act: -0.0000

Data Index: 1357665 (C4 (Web Text))

Max Activating Token Index: 94

Text #14

Max Range: 3.2225. Min Range: -3.2225

Max Act: 2.5234. Min Act: -0.0000

Data Index: 14040 (C4 (Web Text))

Max Activating Token Index: 389

Text #15

Max Range: 3.2225. Min Range: -3.2225

Max Act: 2.3890. Min Act: -0.0000

Data Index: 272122 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 3.2225. Min Range: -3.2225

Max Act: 2.2883. Min Act: -0.0001

Data Index: 1186623 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 3.2225. Min Range: -3.2225

Max Act: 2.2662. Min Act: -0.0000

Data Index: 347801 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 3.2225. Min Range: -3.2225

Max Act: 2.4063. Min Act: -0.0001

Data Index: 757608 (C4 (Web Text))

Max Activating Token Index: 227

Text #19

Max Range: 3.2225. Min Range: -3.2225

Max Act: 2.3261. Min Act: -0.0001

Data Index: 417721 (C4 (Web Text))

Max Activating Token Index: 10