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

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

Neuron 4489 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.3961. Min Act: -0.0000

Data Index: 831398 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.3352. Min Act: -0.0000

Data Index: 1532370 (Python Code)

Max Activating Token Index: 472

Text #2

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.3326. Min Act: -0.0000

Data Index: 1137736 (C4 (Web Text))

Max Activating Token Index: 500

Text #3

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.3541. Min Act: -0.0000

Data Index: 259158 (C4 (Web Text))

Max Activating Token Index: 193

Text #4

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.3122. Min Act: -0.0000

Data Index: 1605049 (Python Code)

Max Activating Token Index: 253

Text #5

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.3106. Min Act: -0.0000

Data Index: 409222 (C4 (Web Text))

Max Activating Token Index: 340

Text #6

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.3144. Min Act: -0.0000

Data Index: 1583810 (Python Code)

Max Activating Token Index: 550

Text #7

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.2997. Min Act: -0.0000

Data Index: 1641989 (Python Code)

Max Activating Token Index: 225

Text #8

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.2911. Min Act: -0.0000

Data Index: 301469 (C4 (Web Text))

Max Activating Token Index: 232

Text #9

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.3106. Min Act: -0.0000

Data Index: 925298 (C4 (Web Text))

Max Activating Token Index: 346

Text #10

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.3019. Min Act: -0.0000

Data Index: 145993 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.2962. Min Act: -0.0000

Data Index: 1656434 (Python Code)

Max Activating Token Index: 607

Text #12

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.2863. Min Act: -0.0000

Data Index: 1459942 (Python Code)

Max Activating Token Index: 675

Text #13

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.2952. Min Act: -0.0000

Data Index: 1626000 (Python Code)

Max Activating Token Index: 293

Text #14

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.2841. Min Act: -0.0000

Data Index: 570117 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.2907. Min Act: -0.0000

Data Index: 1648391 (Python Code)

Max Activating Token Index: 155

Text #16

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.2945. Min Act: -0.0000

Data Index: 1188810 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.2699. Min Act: -0.0000

Data Index: 1606789 (Python Code)

Max Activating Token Index: 449

Text #18

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.2827. Min Act: -0.0000

Data Index: 19997 (C4 (Web Text))

Max Activating Token Index: 816

Text #19

Max Range: 0.3961. Min Range: -0.3961

Max Act: 0.2681. Min Act: -0.0000

Data Index: 1167948 (C4 (Web Text))

Max Activating Token Index: 668