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

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

Neuron 4903 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4458. Min Range: -3.4458

Max Act: 3.4458. Min Act: -0.0000

Data Index: 937607 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 3.4458. Min Range: -3.4458

Max Act: 3.3385. Min Act: -0.0000

Data Index: 637588 (C4 (Web Text))

Max Activating Token Index: 975

Text #2

Max Range: 3.4458. Min Range: -3.4458

Max Act: 3.1220. Min Act: -0.0000

Data Index: 677304 (C4 (Web Text))

Max Activating Token Index: 438

Text #3

Max Range: 3.4458. Min Range: -3.4458

Max Act: 3.3120. Min Act: -0.0000

Data Index: 1038838 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 3.4458. Min Range: -3.4458

Max Act: 2.9891. Min Act: -0.0000

Data Index: 177853 (C4 (Web Text))

Max Activating Token Index: 662

Text #5

Max Range: 3.4458. Min Range: -3.4458

Max Act: 3.0714. Min Act: -0.0000

Data Index: 1125036 (C4 (Web Text))

Max Activating Token Index: 982

Text #6

Max Range: 3.4458. Min Range: -3.4458

Max Act: 3.0506. Min Act: -0.0000

Data Index: 793416 (C4 (Web Text))

Max Activating Token Index: 929

Text #7

Max Range: 3.4458. Min Range: -3.4458

Max Act: 3.0474. Min Act: -0.0000

Data Index: 832781 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 3.4458. Min Range: -3.4458

Max Act: 3.0333. Min Act: -0.0000

Data Index: 894218 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 3.4458. Min Range: -3.4458

Max Act: 2.8837. Min Act: -0.0000

Data Index: 134985 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 3.4458. Min Range: -3.4458

Max Act: 2.5626. Min Act: -0.0000

Data Index: 1288945 (C4 (Web Text))

Max Activating Token Index: 505

Text #11

Max Range: 3.4458. Min Range: -3.4458

Max Act: 2.6930. Min Act: -0.0000

Data Index: 1278447 (C4 (Web Text))

Max Activating Token Index: 918

Text #12

Max Range: 3.4458. Min Range: -3.4458

Max Act: 2.6935. Min Act: -0.0000

Data Index: 1254558 (C4 (Web Text))

Max Activating Token Index: 559

Text #13

Max Range: 3.4458. Min Range: -3.4458

Max Act: 2.6547. Min Act: -0.0000

Data Index: 791525 (C4 (Web Text))

Max Activating Token Index: 668

Text #14

Max Range: 3.4458. Min Range: -3.4458

Max Act: 2.6020. Min Act: -0.0000

Data Index: 908217 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 3.4458. Min Range: -3.4458

Max Act: 2.5378. Min Act: -0.0000

Data Index: 569940 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 3.4458. Min Range: -3.4458

Max Act: 2.4124. Min Act: -0.0000

Data Index: 669912 (C4 (Web Text))

Max Activating Token Index: 1020

Text #17

Max Range: 3.4458. Min Range: -3.4458

Max Act: 2.5281. Min Act: -0.0000

Data Index: 948560 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 3.4458. Min Range: -3.4458

Max Act: 2.4004. Min Act: -0.0000

Data Index: 49642 (C4 (Web Text))

Max Activating Token Index: 674

Text #19

Max Range: 3.4458. Min Range: -3.4458

Max Act: 2.4903. Min Act: -0.0000

Data Index: 510570 (C4 (Web Text))

Max Activating Token Index: 489