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

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

Neuron 1237 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0347. Min Range: -2.0347

Max Act: 2.0347. Min Act: -0.0000

Data Index: 723456 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 2.0347. Min Range: -2.0347

Max Act: 1.7864. Min Act: -0.0000

Data Index: 427637 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 2.0347. Min Range: -2.0347

Max Act: 1.8228. Min Act: -0.0000

Data Index: 644990 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 2.0347. Min Range: -2.0347

Max Act: 1.7792. Min Act: -0.0000

Data Index: 550153 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 2.0347. Min Range: -2.0347

Max Act: 1.7003. Min Act: -0.0000

Data Index: 1556595 (Python Code)

Max Activating Token Index: 182

Text #5

Max Range: 2.0347. Min Range: -2.0347

Max Act: 1.7660. Min Act: -0.0000

Data Index: 538015 (C4 (Web Text))

Max Activating Token Index: 473

Text #6

Max Range: 2.0347. Min Range: -2.0347

Max Act: 1.6181. Min Act: -0.0000

Data Index: 814436 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 2.0347. Min Range: -2.0347

Max Act: 1.5495. Min Act: -0.0000

Data Index: 740690 (C4 (Web Text))

Max Activating Token Index: 720

Text #8

Max Range: 2.0347. Min Range: -2.0347

Max Act: 1.6662. Min Act: -0.0000

Data Index: 1166804 (C4 (Web Text))

Max Activating Token Index: 264

Text #9

Max Range: 2.0347. Min Range: -2.0347

Max Act: 1.5232. Min Act: -0.0000

Data Index: 644364 (C4 (Web Text))

Max Activating Token Index: 698

Text #10

Max Range: 2.0347. Min Range: -2.0347

Max Act: 1.6915. Min Act: -0.0000

Data Index: 507499 (C4 (Web Text))

Max Activating Token Index: 975

Text #11

Max Range: 2.0347. Min Range: -2.0347

Max Act: 1.5729. Min Act: -0.0000

Data Index: 1046392 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 2.0347. Min Range: -2.0347

Max Act: 1.5749. Min Act: -0.0000

Data Index: 624560 (C4 (Web Text))

Max Activating Token Index: 688

Text #13

Max Range: 2.0347. Min Range: -2.0347

Max Act: 1.4792. Min Act: -0.0000

Data Index: 43066 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 2.0347. Min Range: -2.0347

Max Act: 1.5648. Min Act: -0.0000

Data Index: 94698 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 2.0347. Min Range: -2.0347

Max Act: 1.6013. Min Act: -0.0000

Data Index: 30487 (C4 (Web Text))

Max Activating Token Index: 461

Text #16

Max Range: 2.0347. Min Range: -2.0347

Max Act: 1.4327. Min Act: -0.0000

Data Index: 516653 (C4 (Web Text))

Max Activating Token Index: 491

Text #17

Max Range: 2.0347. Min Range: -2.0347

Max Act: 1.6019. Min Act: -0.0000

Data Index: 646351 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 2.0347. Min Range: -2.0347

Max Act: 1.6295. Min Act: -0.0000

Data Index: 593342 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 2.0347. Min Range: -2.0347

Max Act: 1.4545. Min Act: -0.0000

Data Index: 610646 (C4 (Web Text))

Max Activating Token Index: 328