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

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

Neuron 3347 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.0862. Min Range: -3.0862

Max Act: 3.0862. Min Act: -0.0000

Data Index: 635075 (C4 (Web Text))

Max Activating Token Index: 240

Text #1

Max Range: 3.0862. Min Range: -3.0862

Max Act: 2.7195. Min Act: -0.0001

Data Index: 1076591 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 3.0862. Min Range: -3.0862

Max Act: 2.9922. Min Act: -0.0001

Data Index: 778673 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 3.0862. Min Range: -3.0862

Max Act: 2.7714. Min Act: -0.0001

Data Index: 1282183 (C4 (Web Text))

Max Activating Token Index: 516

Text #4

Max Range: 3.0862. Min Range: -3.0862

Max Act: 2.6112. Min Act: -0.0000

Data Index: 296981 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 3.0862. Min Range: -3.0862

Max Act: 2.3644. Min Act: -0.0001

Data Index: 730987 (C4 (Web Text))

Max Activating Token Index: 281

Text #6

Max Range: 3.0862. Min Range: -3.0862

Max Act: 2.9697. Min Act: -0.0000

Data Index: 1041992 (C4 (Web Text))

Max Activating Token Index: 409

Text #7

Max Range: 3.0862. Min Range: -3.0862

Max Act: 2.7055. Min Act: -0.0000

Data Index: 1110705 (C4 (Web Text))

Max Activating Token Index: 959

Text #8

Max Range: 3.0862. Min Range: -3.0862

Max Act: 2.4309. Min Act: -0.0000

Data Index: 532581 (C4 (Web Text))

Max Activating Token Index: 359

Text #9

Max Range: 3.0862. Min Range: -3.0862

Max Act: 2.7275. Min Act: -0.0001

Data Index: 117608 (C4 (Web Text))

Max Activating Token Index: 716

Text #10

Max Range: 3.0862. Min Range: -3.0862

Max Act: 2.3594. Min Act: -0.0001

Data Index: 1112724 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 3.0862. Min Range: -3.0862

Max Act: 2.5830. Min Act: -0.0001

Data Index: 730122 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 3.0862. Min Range: -3.0862

Max Act: 2.4255. Min Act: -0.0001

Data Index: 956709 (C4 (Web Text))

Max Activating Token Index: 204

Text #13

Max Range: 3.0862. Min Range: -3.0862

Max Act: 2.5537. Min Act: -0.0001

Data Index: 729694 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 3.0862. Min Range: -3.0862

Max Act: 2.4188. Min Act: -0.0000

Data Index: 411720 (C4 (Web Text))

Max Activating Token Index: 712

Text #15

Max Range: 3.0862. Min Range: -3.0862

Max Act: 2.6931. Min Act: -0.0000

Data Index: 1012029 (C4 (Web Text))

Max Activating Token Index: 662

Text #16

Max Range: 3.0862. Min Range: -3.0862

Max Act: 2.9067. Min Act: -0.0001

Data Index: 173457 (C4 (Web Text))

Max Activating Token Index: 244

Text #17

Max Range: 3.0862. Min Range: -3.0862

Max Act: 2.8944. Min Act: -0.0001

Data Index: 931715 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 3.0862. Min Range: -3.0862

Max Act: 2.7624. Min Act: -0.0000

Data Index: 433052 (C4 (Web Text))

Max Activating Token Index: 603

Text #19

Max Range: 3.0862. Min Range: -3.0862

Max Act: 2.7467. Min Act: -0.0001

Data Index: 437570 (C4 (Web Text))

Max Activating Token Index: 732