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

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

Neuron 1990 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7054. Min Range: -1.7054

Max Act: 1.7054. Min Act: -0.0000

Data Index: 1280823 (C4 (Web Text))

Max Activating Token Index: 855

Text #1

Max Range: 1.7054. Min Range: -1.7054

Max Act: 1.6337. Min Act: -0.0000

Data Index: 1137418 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 1.7054. Min Range: -1.7054

Max Act: 1.5143. Min Act: -0.0000

Data Index: 1116758 (C4 (Web Text))

Max Activating Token Index: 1010

Text #3

Max Range: 1.7054. Min Range: -1.7054

Max Act: 1.4626. Min Act: -0.0000

Data Index: 710919 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 1.7054. Min Range: -1.7054

Max Act: 1.4734. Min Act: -0.0000

Data Index: 603089 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 1.7054. Min Range: -1.7054

Max Act: 1.3321. Min Act: -0.0000

Data Index: 64392 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 1.7054. Min Range: -1.7054

Max Act: 1.3345. Min Act: -0.0000

Data Index: 93168 (C4 (Web Text))

Max Activating Token Index: 694

Text #7

Max Range: 1.7054. Min Range: -1.7054

Max Act: 1.3670. Min Act: -0.0000

Data Index: 254771 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 1.7054. Min Range: -1.7054

Max Act: 1.3517. Min Act: -0.0000

Data Index: 1080893 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 1.7054. Min Range: -1.7054

Max Act: 1.2942. Min Act: -0.0000

Data Index: 728345 (C4 (Web Text))

Max Activating Token Index: 476

Text #10

Max Range: 1.7054. Min Range: -1.7054

Max Act: 1.4004. Min Act: -0.0000

Data Index: 369317 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 1.7054. Min Range: -1.7054

Max Act: 1.2387. Min Act: -0.0000

Data Index: 546152 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 1.7054. Min Range: -1.7054

Max Act: 1.1416. Min Act: -0.0000

Data Index: 1140884 (C4 (Web Text))

Max Activating Token Index: 748

Text #13

Max Range: 1.7054. Min Range: -1.7054

Max Act: 1.1796. Min Act: -0.0000

Data Index: 1475072 (Python Code)

Max Activating Token Index: 736

Text #14

Max Range: 1.7054. Min Range: -1.7054

Max Act: 1.2402. Min Act: -0.0000

Data Index: 315274 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 1.7054. Min Range: -1.7054

Max Act: 1.2742. Min Act: -0.0000

Data Index: 1256117 (C4 (Web Text))

Max Activating Token Index: 200

Text #16

Max Range: 1.7054. Min Range: -1.7054

Max Act: 1.2850. Min Act: -0.0000

Data Index: 350906 (C4 (Web Text))

Max Activating Token Index: 358

Text #17

Max Range: 1.7054. Min Range: -1.7054

Max Act: 1.2865. Min Act: -0.0000

Data Index: 839438 (C4 (Web Text))

Max Activating Token Index: 780

Text #18

Max Range: 1.7054. Min Range: -1.7054

Max Act: 1.2995. Min Act: -0.0000

Data Index: 782334 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 1.7054. Min Range: -1.7054

Max Act: 1.1426. Min Act: -0.0000

Data Index: 513379 (C4 (Web Text))

Max Activating Token Index: 963