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

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

Neuron 3470 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: 0.3393. Min Range: -0.3393

Max Act: 0.3393. Min Act: -0.0001

Data Index: 917852 (C4 (Web Text))

Max Activating Token Index: 661

Text #1

Max Range: 0.3393. Min Range: -0.3393

Max Act: 0.3272. Min Act: -0.0001

Data Index: 149819 (C4 (Web Text))

Max Activating Token Index: 281

Text #2

Max Range: 0.3393. Min Range: -0.3393

Max Act: 0.3083. Min Act: -0.0001

Data Index: 1474827 (Python Code)

Max Activating Token Index: 902

Text #3

Max Range: 0.3393. Min Range: -0.3393

Max Act: 0.3243. Min Act: -0.0001

Data Index: 438712 (C4 (Web Text))

Max Activating Token Index: 990

Text #4

Max Range: 0.3393. Min Range: -0.3393

Max Act: 0.3294. Min Act: -0.0001

Data Index: 32732 (C4 (Web Text))

Max Activating Token Index: 318

Text #5

Max Range: 0.3393. Min Range: -0.3393

Max Act: 0.3024. Min Act: -0.0001

Data Index: 386919 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 0.3393. Min Range: -0.3393

Max Act: 0.3037. Min Act: -0.0001

Data Index: 1404135 (Python Code)

Max Activating Token Index: 429

Text #7

Max Range: 0.3393. Min Range: -0.3393

Max Act: 0.3020. Min Act: -0.0001

Data Index: 1477341 (Python Code)

Max Activating Token Index: 716

Text #8

Max Range: 0.3393. Min Range: -0.3393

Max Act: 0.3152. Min Act: -0.0001

Data Index: 290131 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 0.3393. Min Range: -0.3393

Max Act: 0.2935. Min Act: -0.0001

Data Index: 273370 (C4 (Web Text))

Max Activating Token Index: 501

Text #10

Max Range: 0.3393. Min Range: -0.3393

Max Act: 0.2519. Min Act: -0.0001

Data Index: 252346 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 0.3393. Min Range: -0.3393

Max Act: 0.3031. Min Act: -0.0001

Data Index: 1553208 (Python Code)

Max Activating Token Index: 691

Text #12

Max Range: 0.3393. Min Range: -0.3393

Max Act: 0.2704. Min Act: -0.0001

Data Index: 1589118 (Python Code)

Max Activating Token Index: 749

Text #13

Max Range: 0.3393. Min Range: -0.3393

Max Act: 0.2661. Min Act: -0.0001

Data Index: 1454297 (Python Code)

Max Activating Token Index: 524

Text #14

Max Range: 0.3393. Min Range: -0.3393

Max Act: 0.2727. Min Act: -0.0001

Data Index: 265721 (C4 (Web Text))

Max Activating Token Index: 934

Text #15

Max Range: 0.3393. Min Range: -0.3393

Max Act: 0.2639. Min Act: -0.0000

Data Index: 826890 (C4 (Web Text))

Max Activating Token Index: 712

Text #16

Max Range: 0.3393. Min Range: -0.3393

Max Act: 0.2628. Min Act: -0.0001

Data Index: 1482422 (Python Code)

Max Activating Token Index: 482

Text #17

Max Range: 0.3393. Min Range: -0.3393

Max Act: 0.2760. Min Act: -0.0001

Data Index: 478881 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 0.3393. Min Range: -0.3393

Max Act: 0.2591. Min Act: -0.0001

Data Index: 815046 (C4 (Web Text))

Max Activating Token Index: 511

Text #19

Max Range: 0.3393. Min Range: -0.3393

Max Act: 0.2570. Min Act: -0.0001

Data Index: 1622146 (Python Code)

Max Activating Token Index: 242