Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1419 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.3220. Min Act: -0.0001

Data Index: 582115 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2774. Min Act: -0.0001

Data Index: 531930 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2907. Min Act: -0.0001

Data Index: 705988 (C4 (Web Text))

Max Activating Token Index: 894

Text #3

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2978. Min Act: -0.0001

Data Index: 203045 (C4 (Web Text))

Max Activating Token Index: 810

Text #4

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2612. Min Act: -0.0001

Data Index: 924403 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2883. Min Act: -0.0001

Data Index: 1227849 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2766. Min Act: -0.0001

Data Index: 1073864 (C4 (Web Text))

Max Activating Token Index: 981

Text #7

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.3122. Min Act: -0.0001

Data Index: 1311379 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2992. Min Act: -0.0001

Data Index: 565011 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2892. Min Act: -0.0001

Data Index: 958809 (C4 (Web Text))

Max Activating Token Index: 963

Text #10

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2723. Min Act: -0.0001

Data Index: 256863 (C4 (Web Text))

Max Activating Token Index: 529

Text #11

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2733. Min Act: -0.0001

Data Index: 650779 (C4 (Web Text))

Max Activating Token Index: 463

Text #12

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2713. Min Act: -0.0001

Data Index: 911573 (C4 (Web Text))

Max Activating Token Index: 647

Text #13

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2678. Min Act: -0.0001

Data Index: 754238 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2655. Min Act: -0.0001

Data Index: 750559 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2745. Min Act: -0.0001

Data Index: 631575 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2395. Min Act: -0.0001

Data Index: 451257 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2479. Min Act: -0.0001

Data Index: 423061 (C4 (Web Text))

Max Activating Token Index: 435

Text #18

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2637. Min Act: -0.0001

Data Index: 29181 (C4 (Web Text))

Max Activating Token Index: 211

Text #19

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2527. Min Act: -0.0001

Data Index: 721898 (C4 (Web Text))

Max Activating Token Index: 102