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

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

Neuron 3551 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4633. Min Act: -0.0001

Data Index: 785117 (C4 (Web Text))

Max Activating Token Index: 708

Text #1

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4881. Min Act: -0.0001

Data Index: 281446 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4536. Min Act: -0.0000

Data Index: 384094 (C4 (Web Text))

Max Activating Token Index: 726

Text #3

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4567. Min Act: -0.0000

Data Index: 503902 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4407. Min Act: -0.0000

Data Index: 804379 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4423. Min Act: -0.0001

Data Index: 158132 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4462. Min Act: -0.0001

Data Index: 780424 (C4 (Web Text))

Max Activating Token Index: 987

Text #7

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4561. Min Act: -0.0001

Data Index: 706109 (C4 (Web Text))

Max Activating Token Index: 1012

Text #8

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4185. Min Act: -0.0001

Data Index: 1102167 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4277. Min Act: -0.0001

Data Index: 871584 (C4 (Web Text))

Max Activating Token Index: 925

Text #10

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4274. Min Act: -0.0001

Data Index: 905430 (C4 (Web Text))

Max Activating Token Index: 887

Text #11

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4032. Min Act: -0.0001

Data Index: 857864 (C4 (Web Text))

Max Activating Token Index: 373

Text #12

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4009. Min Act: -0.0000

Data Index: 501367 (C4 (Web Text))

Max Activating Token Index: 761

Text #13

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4195. Min Act: -0.0001

Data Index: 1211935 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4158. Min Act: -0.0001

Data Index: 799096 (C4 (Web Text))

Max Activating Token Index: 810

Text #15

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4344. Min Act: -0.0001

Data Index: 900363 (C4 (Web Text))

Max Activating Token Index: 243

Text #16

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.3908. Min Act: -0.0000

Data Index: 1342560 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.3939. Min Act: -0.0001

Data Index: 1007417 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.3801. Min Act: -0.0001

Data Index: 462643 (C4 (Web Text))

Max Activating Token Index: 302

Text #19

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.3897. Min Act: -0.0001

Data Index: 391150 (C4 (Web Text))

Max Activating Token Index: 685