Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1230 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.9670. Min Range: -1.9670

Max Act: 1.9670. Min Act: -0.0000

Data Index: 524952 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 1.9670. Min Range: -1.9670

Max Act: 1.7177. Min Act: -0.0000

Data Index: 986508 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 1.9670. Min Range: -1.9670

Max Act: 1.8777. Min Act: -0.0000

Data Index: 919650 (C4 (Web Text))

Max Activating Token Index: 344

Text #3

Max Range: 1.9670. Min Range: -1.9670

Max Act: 1.8823. Min Act: -0.0000

Data Index: 1016431 (C4 (Web Text))

Max Activating Token Index: 594

Text #4

Max Range: 1.9670. Min Range: -1.9670

Max Act: 1.8304. Min Act: -0.0000

Data Index: 812176 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 1.9670. Min Range: -1.9670

Max Act: 1.8193. Min Act: -0.0000

Data Index: 706539 (C4 (Web Text))

Max Activating Token Index: 538

Text #6

Max Range: 1.9670. Min Range: -1.9670

Max Act: 1.8015. Min Act: -0.0000

Data Index: 876260 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 1.9670. Min Range: -1.9670

Max Act: 1.5333. Min Act: -0.0000

Data Index: 1240870 (C4 (Web Text))

Max Activating Token Index: 491

Text #8

Max Range: 1.9670. Min Range: -1.9670

Max Act: 1.5168. Min Act: -0.0000

Data Index: 845836 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 1.9670. Min Range: -1.9670

Max Act: 1.6728. Min Act: -0.0000

Data Index: 277089 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 1.9670. Min Range: -1.9670

Max Act: 1.4910. Min Act: -0.0000

Data Index: 1212901 (C4 (Web Text))

Max Activating Token Index: 610

Text #11

Max Range: 1.9670. Min Range: -1.9670

Max Act: 1.4631. Min Act: -0.0000

Data Index: 698320 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 1.9670. Min Range: -1.9670

Max Act: 1.5511. Min Act: -0.0000

Data Index: 683748 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 1.9670. Min Range: -1.9670

Max Act: 1.5573. Min Act: -0.0000

Data Index: 1335975 (C4 (Web Text))

Max Activating Token Index: 982

Text #14

Max Range: 1.9670. Min Range: -1.9670

Max Act: 1.4599. Min Act: -0.0000

Data Index: 1187469 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 1.9670. Min Range: -1.9670

Max Act: 1.6541. Min Act: -0.0000

Data Index: 893658 (C4 (Web Text))

Max Activating Token Index: 770

Text #16

Max Range: 1.9670. Min Range: -1.9670

Max Act: 1.3802. Min Act: -0.0000

Data Index: 642428 (C4 (Web Text))

Max Activating Token Index: 374

Text #17

Max Range: 1.9670. Min Range: -1.9670

Max Act: 1.4796. Min Act: -0.0000

Data Index: 155798 (C4 (Web Text))

Max Activating Token Index: 621

Text #18

Max Range: 1.9670. Min Range: -1.9670

Max Act: 1.5640. Min Act: -0.0000

Data Index: 741745 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 1.9670. Min Range: -1.9670

Max Act: 1.3695. Min Act: -0.0000

Data Index: 534928 (C4 (Web Text))

Max Activating Token Index: 422