Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1161 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.5388. Min Range: -2.5388

Max Act: 2.5388. Min Act: -0.0000

Data Index: 110122 (C4 (Web Text))

Max Activating Token Index: 731

Text #1

Max Range: 2.5388. Min Range: -2.5388

Max Act: 1.9332. Min Act: -0.0000

Data Index: 1311568 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 2.5388. Min Range: -2.5388

Max Act: 1.9754. Min Act: -0.0000

Data Index: 1015913 (C4 (Web Text))

Max Activating Token Index: 485

Text #3

Max Range: 2.5388. Min Range: -2.5388

Max Act: 1.6674. Min Act: -0.0000

Data Index: 61799 (C4 (Web Text))

Max Activating Token Index: 778

Text #4

Max Range: 2.5388. Min Range: -2.5388

Max Act: 2.1762. Min Act: -0.0000

Data Index: 672511 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 2.5388. Min Range: -2.5388

Max Act: 1.9543. Min Act: -0.0000

Data Index: 804530 (C4 (Web Text))

Max Activating Token Index: 869

Text #6

Max Range: 2.5388. Min Range: -2.5388

Max Act: 1.8213. Min Act: -0.0000

Data Index: 857657 (C4 (Web Text))

Max Activating Token Index: 398

Text #7

Max Range: 2.5388. Min Range: -2.5388

Max Act: 1.9116. Min Act: -0.0000

Data Index: 917831 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 2.5388. Min Range: -2.5388

Max Act: 1.8030. Min Act: -0.0000

Data Index: 251537 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 2.5388. Min Range: -2.5388

Max Act: 2.0970. Min Act: -0.0000

Data Index: 958364 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 2.5388. Min Range: -2.5388

Max Act: 1.8831. Min Act: -0.0000

Data Index: 225872 (C4 (Web Text))

Max Activating Token Index: 425

Text #11

Max Range: 2.5388. Min Range: -2.5388

Max Act: 1.8742. Min Act: -0.0000

Data Index: 712378 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 2.5388. Min Range: -2.5388

Max Act: 1.7536. Min Act: -0.0000

Data Index: 926386 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 2.5388. Min Range: -2.5388

Max Act: 1.8378. Min Act: -0.0000

Data Index: 492036 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 2.5388. Min Range: -2.5388

Max Act: 1.8475. Min Act: -0.0000

Data Index: 1184094 (C4 (Web Text))

Max Activating Token Index: 573

Text #15

Max Range: 2.5388. Min Range: -2.5388

Max Act: 1.8338. Min Act: -0.0000

Data Index: 64208 (C4 (Web Text))

Max Activating Token Index: 473

Text #16

Max Range: 2.5388. Min Range: -2.5388

Max Act: 1.8293. Min Act: -0.0000

Data Index: 808686 (C4 (Web Text))

Max Activating Token Index: 512

Text #17

Max Range: 2.5388. Min Range: -2.5388

Max Act: 1.8672. Min Act: -0.0000

Data Index: 881667 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 2.5388. Min Range: -2.5388

Max Act: 1.8878. Min Act: -0.0000

Data Index: 333579 (C4 (Web Text))

Max Activating Token Index: 295

Text #19

Max Range: 2.5388. Min Range: -2.5388

Max Act: 1.7591. Min Act: -0.0000

Data Index: 429656 (C4 (Web Text))

Max Activating Token Index: 5