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

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

Neuron 4253 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6101. Min Range: -2.6101

Max Act: 2.5841. Min Act: -0.0000

Data Index: 302986 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 2.6101. Min Range: -2.6101

Max Act: 2.5427. Min Act: -0.0000

Data Index: 214914 (C4 (Web Text))

Max Activating Token Index: 496

Text #2

Max Range: 2.6101. Min Range: -2.6101

Max Act: 2.6101. Min Act: -0.0000

Data Index: 1319862 (C4 (Web Text))

Max Activating Token Index: 530

Text #3

Max Range: 2.6101. Min Range: -2.6101

Max Act: 2.5381. Min Act: -0.0000

Data Index: 1024561 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 2.6101. Min Range: -2.6101

Max Act: 2.5318. Min Act: -0.0001

Data Index: 986844 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 2.6101. Min Range: -2.6101

Max Act: 2.5093. Min Act: -0.0000

Data Index: 938963 (C4 (Web Text))

Max Activating Token Index: 690

Text #6

Max Range: 2.6101. Min Range: -2.6101

Max Act: 2.4328. Min Act: -0.0000

Data Index: 494176 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 2.6101. Min Range: -2.6101

Max Act: 2.4129. Min Act: -0.0000

Data Index: 449898 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 2.6101. Min Range: -2.6101

Max Act: 2.2648. Min Act: -0.0000

Data Index: 1117393 (C4 (Web Text))

Max Activating Token Index: 152

Text #9

Max Range: 2.6101. Min Range: -2.6101

Max Act: 2.2402. Min Act: -0.0000

Data Index: 812326 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 2.6101. Min Range: -2.6101

Max Act: 2.2281. Min Act: -0.0000

Data Index: 281547 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 2.6101. Min Range: -2.6101

Max Act: 2.0957. Min Act: -0.0000

Data Index: 600996 (C4 (Web Text))

Max Activating Token Index: 872

Text #12

Max Range: 2.6101. Min Range: -2.6101

Max Act: 2.1796. Min Act: -0.0000

Data Index: 1571829 (Python Code)

Max Activating Token Index: 244

Text #13

Max Range: 2.6101. Min Range: -2.6101

Max Act: 2.2132. Min Act: -0.0000

Data Index: 1084102 (C4 (Web Text))

Max Activating Token Index: 530

Text #14

Max Range: 2.6101. Min Range: -2.6101

Max Act: 2.0211. Min Act: -0.0000

Data Index: 706634 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 2.6101. Min Range: -2.6101

Max Act: 2.0573. Min Act: -0.0001

Data Index: 1114816 (C4 (Web Text))

Max Activating Token Index: 481

Text #16

Max Range: 2.6101. Min Range: -2.6101

Max Act: 1.9549. Min Act: -0.0000

Data Index: 17492 (C4 (Web Text))

Max Activating Token Index: 1014

Text #17

Max Range: 2.6101. Min Range: -2.6101

Max Act: 1.9488. Min Act: -0.0000

Data Index: 879130 (C4 (Web Text))

Max Activating Token Index: 890

Text #18

Max Range: 2.6101. Min Range: -2.6101

Max Act: 2.0340. Min Act: -0.0000

Data Index: 594427 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 2.6101. Min Range: -2.6101

Max Act: 2.0377. Min Act: -0.0000

Data Index: 1342023 (C4 (Web Text))

Max Activating Token Index: 368