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

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

Neuron 4928 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8781. Min Range: -1.8781

Max Act: 1.8781. Min Act: -0.0001

Data Index: 696405 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 1.8781. Min Range: -1.8781

Max Act: 1.6665. Min Act: -0.0000

Data Index: 1181203 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 1.8781. Min Range: -1.8781

Max Act: 1.6527. Min Act: -0.0001

Data Index: 430984 (C4 (Web Text))

Max Activating Token Index: 519

Text #3

Max Range: 1.8781. Min Range: -1.8781

Max Act: 1.6337. Min Act: -0.0001

Data Index: 903461 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 1.8781. Min Range: -1.8781

Max Act: 1.6135. Min Act: -0.0001

Data Index: 533592 (C4 (Web Text))

Max Activating Token Index: 878

Text #5

Max Range: 1.8781. Min Range: -1.8781

Max Act: 1.4665. Min Act: -0.0000

Data Index: 1058936 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 1.8781. Min Range: -1.8781

Max Act: 1.5510. Min Act: -0.0000

Data Index: 107703 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 1.8781. Min Range: -1.8781

Max Act: 1.4033. Min Act: -0.0000

Data Index: 43788 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 1.8781. Min Range: -1.8781

Max Act: 1.4086. Min Act: -0.0001

Data Index: 1236593 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 1.8781. Min Range: -1.8781

Max Act: 1.2370. Min Act: -0.0001

Data Index: 1256908 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 1.8781. Min Range: -1.8781

Max Act: 1.3457. Min Act: -0.0001

Data Index: 1248274 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 1.8781. Min Range: -1.8781

Max Act: 1.4569. Min Act: -0.0000

Data Index: 1150240 (C4 (Web Text))

Max Activating Token Index: 293

Text #12

Max Range: 1.8781. Min Range: -1.8781

Max Act: 1.3249. Min Act: -0.0001

Data Index: 855392 (C4 (Web Text))

Max Activating Token Index: 181

Text #13

Max Range: 1.8781. Min Range: -1.8781

Max Act: 1.2584. Min Act: -0.0001

Data Index: 811543 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 1.8781. Min Range: -1.8781

Max Act: 1.2446. Min Act: -0.0001

Data Index: 752356 (C4 (Web Text))

Max Activating Token Index: 532

Text #15

Max Range: 1.8781. Min Range: -1.8781

Max Act: 1.2702. Min Act: -0.0001

Data Index: 304355 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 1.8781. Min Range: -1.8781

Max Act: 1.3039. Min Act: -0.0000

Data Index: 1206287 (C4 (Web Text))

Max Activating Token Index: 25

Text #17

Max Range: 1.8781. Min Range: -1.8781

Max Act: 1.2749. Min Act: -0.0001

Data Index: 124762 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 1.8781. Min Range: -1.8781

Max Act: 1.3037. Min Act: -0.0001

Data Index: 769742 (C4 (Web Text))

Max Activating Token Index: 957

Text #19

Max Range: 1.8781. Min Range: -1.8781

Max Act: 1.3477. Min Act: -0.0001

Data Index: 1257764 (C4 (Web Text))

Max Activating Token Index: 189