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

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

Neuron 2633 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2033. Min Range: -3.2033

Max Act: 3.2033. Min Act: -0.0000

Data Index: 252510 (C4 (Web Text))

Max Activating Token Index: 1011

Text #1

Max Range: 3.2033. Min Range: -3.2033

Max Act: 3.0290. Min Act: -0.0000

Data Index: 318597 (C4 (Web Text))

Max Activating Token Index: 535

Text #2

Max Range: 3.2033. Min Range: -3.2033

Max Act: 2.7558. Min Act: -0.0000

Data Index: 932279 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 3.2033. Min Range: -3.2033

Max Act: 2.6800. Min Act: -0.0000

Data Index: 921852 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 3.2033. Min Range: -3.2033

Max Act: 2.2335. Min Act: -0.0000

Data Index: 494914 (C4 (Web Text))

Max Activating Token Index: 927

Text #5

Max Range: 3.2033. Min Range: -3.2033

Max Act: 2.4981. Min Act: -0.0000

Data Index: 45932 (C4 (Web Text))

Max Activating Token Index: 236

Text #6

Max Range: 3.2033. Min Range: -3.2033

Max Act: 2.2612. Min Act: -0.0000

Data Index: 130055 (C4 (Web Text))

Max Activating Token Index: 317

Text #7

Max Range: 3.2033. Min Range: -3.2033

Max Act: 2.4617. Min Act: -0.0000

Data Index: 672279 (C4 (Web Text))

Max Activating Token Index: 619

Text #8

Max Range: 3.2033. Min Range: -3.2033

Max Act: 2.2704. Min Act: -0.0000

Data Index: 829939 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 3.2033. Min Range: -3.2033

Max Act: 2.2234. Min Act: -0.0000

Data Index: 826985 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 3.2033. Min Range: -3.2033

Max Act: 2.0690. Min Act: -0.0000

Data Index: 579741 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 3.2033. Min Range: -3.2033

Max Act: 2.0347. Min Act: -0.0000

Data Index: 1258458 (C4 (Web Text))

Max Activating Token Index: 456

Text #12

Max Range: 3.2033. Min Range: -3.2033

Max Act: 2.2453. Min Act: -0.0000

Data Index: 585077 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 3.2033. Min Range: -3.2033

Max Act: 2.1338. Min Act: -0.0000

Data Index: 386320 (C4 (Web Text))

Max Activating Token Index: 525

Text #14

Max Range: 3.2033. Min Range: -3.2033

Max Act: 2.0053. Min Act: -0.0000

Data Index: 307626 (C4 (Web Text))

Max Activating Token Index: 489

Text #15

Max Range: 3.2033. Min Range: -3.2033

Max Act: 2.0243. Min Act: -0.0000

Data Index: 1198877 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 3.2033. Min Range: -3.2033

Max Act: 2.0284. Min Act: -0.0000

Data Index: 1084129 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 3.2033. Min Range: -3.2033

Max Act: 2.0449. Min Act: -0.0000

Data Index: 1241884 (C4 (Web Text))

Max Activating Token Index: 241

Text #18

Max Range: 3.2033. Min Range: -3.2033

Max Act: 1.9076. Min Act: -0.0000

Data Index: 116964 (C4 (Web Text))

Max Activating Token Index: 752

Text #19

Max Range: 3.2033. Min Range: -3.2033

Max Act: 2.0160. Min Act: -0.0000

Data Index: 781168 (C4 (Web Text))

Max Activating Token Index: 855