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

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

Neuron 633 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.4425. Min Act: -0.0000

Data Index: 385871 (C4 (Web Text))

Max Activating Token Index: 805

Text #1

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.3937. Min Act: -0.0001

Data Index: 603278 (C4 (Web Text))

Max Activating Token Index: 310

Text #2

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.3465. Min Act: -0.0001

Data Index: 928408 (C4 (Web Text))

Max Activating Token Index: 274

Text #3

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.3259. Min Act: -0.0000

Data Index: 53574 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.3294. Min Act: -0.0001

Data Index: 1048017 (C4 (Web Text))

Max Activating Token Index: 376

Text #5

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.3122. Min Act: -0.0000

Data Index: 1268578 (C4 (Web Text))

Max Activating Token Index: 464

Text #6

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.3074. Min Act: -0.0000

Data Index: 834745 (C4 (Web Text))

Max Activating Token Index: 777

Text #7

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.2948. Min Act: -0.0000

Data Index: 890180 (C4 (Web Text))

Max Activating Token Index: 571

Text #8

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.3074. Min Act: -0.0000

Data Index: 344447 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.2924. Min Act: -0.0001

Data Index: 289219 (C4 (Web Text))

Max Activating Token Index: 491

Text #10

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.2918. Min Act: -0.0001

Data Index: 1000702 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.2900. Min Act: -0.0000

Data Index: 245403 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.2775. Min Act: -0.0001

Data Index: 447348 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.2837. Min Act: -0.0000

Data Index: 1275649 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.2785. Min Act: -0.0000

Data Index: 457429 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.2696. Min Act: -0.0001

Data Index: 145963 (C4 (Web Text))

Max Activating Token Index: 594

Text #16

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.2856. Min Act: -0.0000

Data Index: 424252 (C4 (Web Text))

Max Activating Token Index: 407

Text #17

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.2949. Min Act: -0.0000

Data Index: 588753 (C4 (Web Text))

Max Activating Token Index: 474

Text #18

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.2659. Min Act: -0.0001

Data Index: 49234 (C4 (Web Text))

Max Activating Token Index: 519

Text #19

Max Range: 0.4425. Min Range: -0.4425

Max Act: 0.2691. Min Act: -0.0000

Data Index: 577785 (C4 (Web Text))

Max Activating Token Index: 665