Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3203 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.5452. Min Act: -0.0000

Data Index: 252798 (C4 (Web Text))

Max Activating Token Index: 247

Text #1

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.5020. Min Act: -0.0000

Data Index: 721168 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.4178. Min Act: -0.0001

Data Index: 528755 (C4 (Web Text))

Max Activating Token Index: 584

Text #3

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.3992. Min Act: -0.0000

Data Index: 514355 (C4 (Web Text))

Max Activating Token Index: 775

Text #4

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.4231. Min Act: -0.0000

Data Index: 454180 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.3973. Min Act: -0.0001

Data Index: 429214 (C4 (Web Text))

Max Activating Token Index: 718

Text #6

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.4029. Min Act: -0.0000

Data Index: 889116 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.4150. Min Act: -0.0000

Data Index: 1331829 (C4 (Web Text))

Max Activating Token Index: 706

Text #8

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.3946. Min Act: -0.0000

Data Index: 23687 (C4 (Web Text))

Max Activating Token Index: 545

Text #9

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.3787. Min Act: -0.0001

Data Index: 823650 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.3546. Min Act: -0.0000

Data Index: 1299761 (C4 (Web Text))

Max Activating Token Index: 491

Text #11

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.3620. Min Act: -0.0001

Data Index: 518016 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.3588. Min Act: -0.0000

Data Index: 650841 (C4 (Web Text))

Max Activating Token Index: 927

Text #13

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.3842. Min Act: -0.0001

Data Index: 452877 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.3720. Min Act: -0.0000

Data Index: 489904 (C4 (Web Text))

Max Activating Token Index: 902

Text #15

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.3551. Min Act: -0.0000

Data Index: 579347 (C4 (Web Text))

Max Activating Token Index: 701

Text #16

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.3438. Min Act: -0.0000

Data Index: 694866 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.3692. Min Act: -0.0001

Data Index: 402366 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.3414. Min Act: -0.0000

Data Index: 648676 (C4 (Web Text))

Max Activating Token Index: 359

Text #19

Max Range: 0.5452. Min Range: -0.5452

Max Act: 0.3526. Min Act: -0.0001

Data Index: 59146 (C4 (Web Text))

Max Activating Token Index: 244