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

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

Neuron 3117 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4642. Min Range: -0.4642

Max Act: 0.4642. Min Act: -0.0001

Data Index: 258018 (C4 (Web Text))

Max Activating Token Index: 419

Text #1

Max Range: 0.4642. Min Range: -0.4642

Max Act: 0.4584. Min Act: -0.0001

Data Index: 117349 (C4 (Web Text))

Max Activating Token Index: 705

Text #2

Max Range: 0.4642. Min Range: -0.4642

Max Act: 0.4347. Min Act: -0.0001

Data Index: 1044303 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 0.4642. Min Range: -0.4642

Max Act: 0.4035. Min Act: -0.0001

Data Index: 1156201 (C4 (Web Text))

Max Activating Token Index: 700

Text #4

Max Range: 0.4642. Min Range: -0.4642

Max Act: 0.4068. Min Act: -0.0001

Data Index: 966695 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 0.4642. Min Range: -0.4642

Max Act: 0.3659. Min Act: -0.0001

Data Index: 133693 (C4 (Web Text))

Max Activating Token Index: 993

Text #6

Max Range: 0.4642. Min Range: -0.4642

Max Act: 0.4013. Min Act: -0.0001

Data Index: 65699 (C4 (Web Text))

Max Activating Token Index: 125

Text #7

Max Range: 0.4642. Min Range: -0.4642

Max Act: 0.3888. Min Act: -0.0001

Data Index: 1199877 (C4 (Web Text))

Max Activating Token Index: 381

Text #8

Max Range: 0.4642. Min Range: -0.4642

Max Act: 0.3662. Min Act: -0.0001

Data Index: 1135246 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 0.4642. Min Range: -0.4642

Max Act: 0.3533. Min Act: -0.0001

Data Index: 1327366 (C4 (Web Text))

Max Activating Token Index: 150

Text #10

Max Range: 0.4642. Min Range: -0.4642

Max Act: 0.3607. Min Act: -0.0001

Data Index: 412157 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 0.4642. Min Range: -0.4642

Max Act: 0.3596. Min Act: -0.0001

Data Index: 1003891 (C4 (Web Text))

Max Activating Token Index: 218

Text #12

Max Range: 0.4642. Min Range: -0.4642

Max Act: 0.3707. Min Act: -0.0001

Data Index: 937389 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 0.4642. Min Range: -0.4642

Max Act: 0.3385. Min Act: -0.0001

Data Index: 1092136 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 0.4642. Min Range: -0.4642

Max Act: 0.3395. Min Act: -0.0001

Data Index: 1344887 (C4 (Web Text))

Max Activating Token Index: 686

Text #15

Max Range: 0.4642. Min Range: -0.4642

Max Act: 0.3497. Min Act: -0.0001

Data Index: 1536379 (Python Code)

Max Activating Token Index: 971

Text #16

Max Range: 0.4642. Min Range: -0.4642

Max Act: 0.3599. Min Act: -0.0001

Data Index: 460389 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 0.4642. Min Range: -0.4642

Max Act: 0.3236. Min Act: -0.0001

Data Index: 97892 (C4 (Web Text))

Max Activating Token Index: 1018

Text #18

Max Range: 0.4642. Min Range: -0.4642

Max Act: 0.3114. Min Act: -0.0001

Data Index: 450822 (C4 (Web Text))

Max Activating Token Index: 715

Text #19

Max Range: 0.4642. Min Range: -0.4642

Max Act: 0.3463. Min Act: -0.0001

Data Index: 1107843 (C4 (Web Text))

Max Activating Token Index: 580