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

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

Neuron 5528 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2807. Min Range: -4.2807

Max Act: 4.2807. Min Act: -0.0000

Data Index: 826490 (C4 (Web Text))

Max Activating Token Index: 236

Text #1

Max Range: 4.2807. Min Range: -4.2807

Max Act: 3.9707. Min Act: -0.0001

Data Index: 462439 (C4 (Web Text))

Max Activating Token Index: 190

Text #2

Max Range: 4.2807. Min Range: -4.2807

Max Act: 2.9869. Min Act: -0.0000

Data Index: 127570 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 4.2807. Min Range: -4.2807

Max Act: 2.9418. Min Act: -0.0001

Data Index: 640074 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 4.2807. Min Range: -4.2807

Max Act: 2.8216. Min Act: -0.0000

Data Index: 192142 (C4 (Web Text))

Max Activating Token Index: 943

Text #5

Max Range: 4.2807. Min Range: -4.2807

Max Act: 2.4150. Min Act: -0.0001

Data Index: 483250 (C4 (Web Text))

Max Activating Token Index: 403

Text #6

Max Range: 4.2807. Min Range: -4.2807

Max Act: 2.7675. Min Act: -0.0000

Data Index: 1103232 (C4 (Web Text))

Max Activating Token Index: 480

Text #7

Max Range: 4.2807. Min Range: -4.2807

Max Act: 2.7540. Min Act: -0.0000

Data Index: 1055097 (C4 (Web Text))

Max Activating Token Index: 437

Text #8

Max Range: 4.2807. Min Range: -4.2807

Max Act: 2.5513. Min Act: -0.0000

Data Index: 628023 (C4 (Web Text))

Max Activating Token Index: 544

Text #9

Max Range: 4.2807. Min Range: -4.2807

Max Act: 2.7566. Min Act: -0.0000

Data Index: 533569 (C4 (Web Text))

Max Activating Token Index: 525

Text #10

Max Range: 4.2807. Min Range: -4.2807

Max Act: 2.3239. Min Act: -0.0000

Data Index: 409173 (C4 (Web Text))

Max Activating Token Index: 356

Text #11

Max Range: 4.2807. Min Range: -4.2807

Max Act: 2.6670. Min Act: -0.0000

Data Index: 1224188 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 4.2807. Min Range: -4.2807

Max Act: 2.6350. Min Act: -0.0000

Data Index: 1197930 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 4.2807. Min Range: -4.2807

Max Act: 2.5146. Min Act: -0.0000

Data Index: 1262406 (C4 (Web Text))

Max Activating Token Index: 419

Text #14

Max Range: 4.2807. Min Range: -4.2807

Max Act: 2.4043. Min Act: -0.0000

Data Index: 1042812 (C4 (Web Text))

Max Activating Token Index: 525

Text #15

Max Range: 4.2807. Min Range: -4.2807

Max Act: 2.2362. Min Act: -0.0000

Data Index: 687893 (C4 (Web Text))

Max Activating Token Index: 212

Text #16

Max Range: 4.2807. Min Range: -4.2807

Max Act: 2.2209. Min Act: -0.0000

Data Index: 1092804 (C4 (Web Text))

Max Activating Token Index: 392

Text #17

Max Range: 4.2807. Min Range: -4.2807

Max Act: 2.1318. Min Act: -0.0000

Data Index: 95584 (C4 (Web Text))

Max Activating Token Index: 691

Text #18

Max Range: 4.2807. Min Range: -4.2807

Max Act: 2.1400. Min Act: -0.0000

Data Index: 247807 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 4.2807. Min Range: -4.2807

Max Act: 2.1715. Min Act: -0.0001

Data Index: 997789 (C4 (Web Text))

Max Activating Token Index: 982