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

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

Neuron 3121 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.6953. Min Act: -0.0001

Data Index: 787170 (C4 (Web Text))

Max Activating Token Index: 420

Text #1

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.6920. Min Act: -0.0001

Data Index: 75002 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.6405. Min Act: -0.0001

Data Index: 964585 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5851. Min Act: -0.0001

Data Index: 707078 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5974. Min Act: -0.0001

Data Index: 691928 (C4 (Web Text))

Max Activating Token Index: 645

Text #5

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5847. Min Act: -0.0001

Data Index: 1112020 (C4 (Web Text))

Max Activating Token Index: 190

Text #6

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5542. Min Act: -0.0001

Data Index: 841732 (C4 (Web Text))

Max Activating Token Index: 339

Text #7

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5823. Min Act: -0.0001

Data Index: 1259879 (C4 (Web Text))

Max Activating Token Index: 242

Text #8

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5439. Min Act: -0.0001

Data Index: 1232778 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5942. Min Act: -0.0001

Data Index: 424131 (C4 (Web Text))

Max Activating Token Index: 321

Text #10

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5842. Min Act: -0.0001

Data Index: 1199223 (C4 (Web Text))

Max Activating Token Index: 814

Text #11

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5246. Min Act: -0.0001

Data Index: 430777 (C4 (Web Text))

Max Activating Token Index: 237

Text #12

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5262. Min Act: -0.0001

Data Index: 663599 (C4 (Web Text))

Max Activating Token Index: 238

Text #13

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5631. Min Act: -0.0001

Data Index: 1314312 (C4 (Web Text))

Max Activating Token Index: 208

Text #14

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5163. Min Act: -0.0001

Data Index: 803948 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5507. Min Act: -0.0001

Data Index: 685821 (C4 (Web Text))

Max Activating Token Index: 332

Text #16

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5374. Min Act: -0.0001

Data Index: 65692 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5105. Min Act: -0.0001

Data Index: 327911 (C4 (Web Text))

Max Activating Token Index: 954

Text #18

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5230. Min Act: -0.0001

Data Index: 1057511 (C4 (Web Text))

Max Activating Token Index: 354

Text #19

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5255. Min Act: -0.0001

Data Index: 696730 (C4 (Web Text))

Max Activating Token Index: 193