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

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

Neuron 1411 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: 4.4310. Min Range: -4.4310

Max Act: 4.4310. Min Act: -0.0000

Data Index: 502335 (C4 (Web Text))

Max Activating Token Index: 366

Text #1

Max Range: 4.4310. Min Range: -4.4310

Max Act: 4.2669. Min Act: -0.0000

Data Index: 634832 (C4 (Web Text))

Max Activating Token Index: 532

Text #2

Max Range: 4.4310. Min Range: -4.4310

Max Act: 4.1434. Min Act: -0.0000

Data Index: 393123 (C4 (Web Text))

Max Activating Token Index: 707

Text #3

Max Range: 4.4310. Min Range: -4.4310

Max Act: 4.0826. Min Act: -0.0000

Data Index: 1023204 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 4.4310. Min Range: -4.4310

Max Act: 3.9802. Min Act: -0.0000

Data Index: 190279 (C4 (Web Text))

Max Activating Token Index: 791

Text #5

Max Range: 4.4310. Min Range: -4.4310

Max Act: 3.6914. Min Act: -0.0000

Data Index: 1236854 (C4 (Web Text))

Max Activating Token Index: 441

Text #6

Max Range: 4.4310. Min Range: -4.4310

Max Act: 3.6749. Min Act: -0.0000

Data Index: 773654 (C4 (Web Text))

Max Activating Token Index: 65

Text #7

Max Range: 4.4310. Min Range: -4.4310

Max Act: 3.4738. Min Act: -0.0000

Data Index: 768422 (C4 (Web Text))

Max Activating Token Index: 757

Text #8

Max Range: 4.4310. Min Range: -4.4310

Max Act: 3.6420. Min Act: -0.0000

Data Index: 502402 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 4.4310. Min Range: -4.4310

Max Act: 3.5597. Min Act: -0.0000

Data Index: 784269 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 4.4310. Min Range: -4.4310

Max Act: 3.6886. Min Act: -0.0000

Data Index: 72365 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 4.4310. Min Range: -4.4310

Max Act: 3.4193. Min Act: -0.0000

Data Index: 1119409 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 4.4310. Min Range: -4.4310

Max Act: 3.1800. Min Act: -0.0000

Data Index: 205051 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 4.4310. Min Range: -4.4310

Max Act: 3.3195. Min Act: -0.0000

Data Index: 768927 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 4.4310. Min Range: -4.4310

Max Act: 3.0060. Min Act: -0.0000

Data Index: 1304514 (C4 (Web Text))

Max Activating Token Index: 504

Text #15

Max Range: 4.4310. Min Range: -4.4310

Max Act: 3.1439. Min Act: -0.0000

Data Index: 368607 (C4 (Web Text))

Max Activating Token Index: 846

Text #16

Max Range: 4.4310. Min Range: -4.4310

Max Act: 2.9764. Min Act: -0.0000

Data Index: 5040 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 4.4310. Min Range: -4.4310

Max Act: 2.8336. Min Act: -0.0000

Data Index: 953436 (C4 (Web Text))

Max Activating Token Index: 770

Text #18

Max Range: 4.4310. Min Range: -4.4310

Max Act: 2.9667. Min Act: -0.0000

Data Index: 1089538 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 4.4310. Min Range: -4.4310

Max Act: 3.0916. Min Act: -0.0000

Data Index: 855418 (C4 (Web Text))

Max Activating Token Index: 570