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

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

Neuron 620 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9499. Min Range: -2.9499

Max Act: 2.8790. Min Act: -0.0000

Data Index: 416081 (C4 (Web Text))

Max Activating Token Index: 306

Text #1

Max Range: 2.9499. Min Range: -2.9499

Max Act: 2.9499. Min Act: -0.0000

Data Index: 674048 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 2.9499. Min Range: -2.9499

Max Act: 2.6445. Min Act: -0.0000

Data Index: 1163164 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 2.9499. Min Range: -2.9499

Max Act: 2.3706. Min Act: -0.0000

Data Index: 224218 (C4 (Web Text))

Max Activating Token Index: 856

Text #4

Max Range: 2.9499. Min Range: -2.9499

Max Act: 2.3413. Min Act: -0.0000

Data Index: 452400 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 2.9499. Min Range: -2.9499

Max Act: 2.4442. Min Act: -0.0000

Data Index: 866412 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 2.9499. Min Range: -2.9499

Max Act: 2.2950. Min Act: -0.0000

Data Index: 917514 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 2.9499. Min Range: -2.9499

Max Act: 2.2772. Min Act: -0.0000

Data Index: 385949 (C4 (Web Text))

Max Activating Token Index: 110

Text #8

Max Range: 2.9499. Min Range: -2.9499

Max Act: 2.2676. Min Act: -0.0000

Data Index: 1196009 (C4 (Web Text))

Max Activating Token Index: 387

Text #9

Max Range: 2.9499. Min Range: -2.9499

Max Act: 2.2604. Min Act: -0.0000

Data Index: 40662 (C4 (Web Text))

Max Activating Token Index: 919

Text #10

Max Range: 2.9499. Min Range: -2.9499

Max Act: 2.2520. Min Act: -0.0000

Data Index: 72523 (C4 (Web Text))

Max Activating Token Index: 809

Text #11

Max Range: 2.9499. Min Range: -2.9499

Max Act: 2.0986. Min Act: -0.0000

Data Index: 240804 (C4 (Web Text))

Max Activating Token Index: 460

Text #12

Max Range: 2.9499. Min Range: -2.9499

Max Act: 2.0730. Min Act: -0.0000

Data Index: 22580 (C4 (Web Text))

Max Activating Token Index: 922

Text #13

Max Range: 2.9499. Min Range: -2.9499

Max Act: 2.2943. Min Act: -0.0000

Data Index: 475310 (C4 (Web Text))

Max Activating Token Index: 204

Text #14

Max Range: 2.9499. Min Range: -2.9499

Max Act: 2.2929. Min Act: -0.0000

Data Index: 424056 (C4 (Web Text))

Max Activating Token Index: 313

Text #15

Max Range: 2.9499. Min Range: -2.9499

Max Act: 2.1152. Min Act: -0.0000

Data Index: 503995 (C4 (Web Text))

Max Activating Token Index: 391

Text #16

Max Range: 2.9499. Min Range: -2.9499

Max Act: 2.1214. Min Act: -0.0000

Data Index: 716596 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 2.9499. Min Range: -2.9499

Max Act: 2.0901. Min Act: -0.0000

Data Index: 1313008 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 2.9499. Min Range: -2.9499

Max Act: 2.2156. Min Act: -0.0000

Data Index: 1284723 (C4 (Web Text))

Max Activating Token Index: 225

Text #19

Max Range: 2.9499. Min Range: -2.9499

Max Act: 2.0666. Min Act: -0.0000

Data Index: 274040 (C4 (Web Text))

Max Activating Token Index: 189