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

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

Neuron 2280 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: 0.4713. Min Range: -0.4713

Max Act: 0.3699. Min Act: -0.0000

Data Index: 627965 (C4 (Web Text))

Max Activating Token Index: 759

Text #1

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.4713. Min Act: -0.0001

Data Index: 992116 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.3532. Min Act: -0.0001

Data Index: 116484 (C4 (Web Text))

Max Activating Token Index: 430

Text #3

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.3522. Min Act: -0.0001

Data Index: 727653 (C4 (Web Text))

Max Activating Token Index: 71

Text #4

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.3725. Min Act: -0.0001

Data Index: 1235869 (C4 (Web Text))

Max Activating Token Index: 425

Text #5

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.2834. Min Act: -0.0001

Data Index: 642200 (C4 (Web Text))

Max Activating Token Index: 81

Text #6

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.3234. Min Act: -0.0001

Data Index: 462409 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.3334. Min Act: -0.0001

Data Index: 504395 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.3429. Min Act: -0.0001

Data Index: 1216707 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.3001. Min Act: -0.0001

Data Index: 909041 (C4 (Web Text))

Max Activating Token Index: 606

Text #10

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.3409. Min Act: -0.0001

Data Index: 22131 (C4 (Web Text))

Max Activating Token Index: 356

Text #11

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.3175. Min Act: -0.0000

Data Index: 718681 (C4 (Web Text))

Max Activating Token Index: 357

Text #12

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.3407. Min Act: -0.0001

Data Index: 316849 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.2861. Min Act: -0.0001

Data Index: 431614 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.3212. Min Act: -0.0001

Data Index: 429884 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.2872. Min Act: -0.0001

Data Index: 346658 (C4 (Web Text))

Max Activating Token Index: 191

Text #16

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.3202. Min Act: -0.0001

Data Index: 193279 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.3019. Min Act: -0.0001

Data Index: 769773 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.2967. Min Act: -0.0001

Data Index: 1010556 (C4 (Web Text))

Max Activating Token Index: 491

Text #19

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.2962. Min Act: -0.0001

Data Index: 1210432 (C4 (Web Text))

Max Activating Token Index: 128