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

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

Neuron 4554 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0107. Min Range: -2.0107

Max Act: 2.0107. Min Act: -0.0000

Data Index: 822592 (C4 (Web Text))

Max Activating Token Index: 950

Text #1

Max Range: 2.0107. Min Range: -2.0107

Max Act: 1.9466. Min Act: -0.0000

Data Index: 953523 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 2.0107. Min Range: -2.0107

Max Act: 1.6419. Min Act: -0.0000

Data Index: 163311 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 2.0107. Min Range: -2.0107

Max Act: 1.5390. Min Act: -0.0000

Data Index: 1245653 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 2.0107. Min Range: -2.0107

Max Act: 1.4871. Min Act: -0.0000

Data Index: 468205 (C4 (Web Text))

Max Activating Token Index: 47

Text #5

Max Range: 2.0107. Min Range: -2.0107

Max Act: 1.5209. Min Act: -0.0000

Data Index: 314069 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 2.0107. Min Range: -2.0107

Max Act: 1.5050. Min Act: -0.0000

Data Index: 12848 (C4 (Web Text))

Max Activating Token Index: 1015

Text #7

Max Range: 2.0107. Min Range: -2.0107

Max Act: 1.4685. Min Act: -0.0000

Data Index: 212144 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 2.0107. Min Range: -2.0107

Max Act: 1.4298. Min Act: -0.0000

Data Index: 839493 (C4 (Web Text))

Max Activating Token Index: 763

Text #9

Max Range: 2.0107. Min Range: -2.0107

Max Act: 1.3915. Min Act: -0.0000

Data Index: 1306584 (C4 (Web Text))

Max Activating Token Index: 635

Text #10

Max Range: 2.0107. Min Range: -2.0107

Max Act: 1.4197. Min Act: -0.0000

Data Index: 1229494 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 2.0107. Min Range: -2.0107

Max Act: 1.3177. Min Act: -0.0000

Data Index: 1157583 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 2.0107. Min Range: -2.0107

Max Act: 1.3501. Min Act: -0.0000

Data Index: 1231321 (C4 (Web Text))

Max Activating Token Index: 776

Text #13

Max Range: 2.0107. Min Range: -2.0107

Max Act: 1.3017. Min Act: -0.0000

Data Index: 796075 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 2.0107. Min Range: -2.0107

Max Act: 1.2962. Min Act: -0.0000

Data Index: 598758 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 2.0107. Min Range: -2.0107

Max Act: 1.2515. Min Act: -0.0000

Data Index: 708662 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 2.0107. Min Range: -2.0107

Max Act: 1.2491. Min Act: -0.0000

Data Index: 726963 (C4 (Web Text))

Max Activating Token Index: 15

Text #17

Max Range: 2.0107. Min Range: -2.0107

Max Act: 1.2466. Min Act: -0.0000

Data Index: 1091223 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 2.0107. Min Range: -2.0107

Max Act: 1.1967. Min Act: -0.0000

Data Index: 1032064 (C4 (Web Text))

Max Activating Token Index: 515

Text #19

Max Range: 2.0107. Min Range: -2.0107

Max Act: 1.1785. Min Act: -0.0000

Data Index: 669695 (C4 (Web Text))

Max Activating Token Index: 629