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

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

Neuron 4833 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.5547. Min Act: -0.0000

Data Index: 570533 (C4 (Web Text))

Max Activating Token Index: 613

Text #1

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.5283. Min Act: -0.0000

Data Index: 139880 (C4 (Web Text))

Max Activating Token Index: 233

Text #2

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4696. Min Act: -0.0000

Data Index: 1139493 (C4 (Web Text))

Max Activating Token Index: 787

Text #3

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4823. Min Act: -0.0000

Data Index: 854084 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4745. Min Act: -0.0000

Data Index: 243495 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.5110. Min Act: -0.0000

Data Index: 861984 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4825. Min Act: -0.0000

Data Index: 483777 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4409. Min Act: -0.0000

Data Index: 1265690 (C4 (Web Text))

Max Activating Token Index: 359

Text #8

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4427. Min Act: -0.0000

Data Index: 730953 (C4 (Web Text))

Max Activating Token Index: 838

Text #9

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4784. Min Act: -0.0000

Data Index: 89927 (C4 (Web Text))

Max Activating Token Index: 883

Text #10

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4377. Min Act: -0.0000

Data Index: 550730 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4637. Min Act: -0.0000

Data Index: 232609 (C4 (Web Text))

Max Activating Token Index: 152

Text #12

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4509. Min Act: -0.0000

Data Index: 569282 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4401. Min Act: -0.0000

Data Index: 699565 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4456. Min Act: -0.0000

Data Index: 243696 (C4 (Web Text))

Max Activating Token Index: 1019

Text #15

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4310. Min Act: -0.0000

Data Index: 235048 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4175. Min Act: -0.0000

Data Index: 1015929 (C4 (Web Text))

Max Activating Token Index: 906

Text #17

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4208. Min Act: -0.0000

Data Index: 820689 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4073. Min Act: -0.0000

Data Index: 222152 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4024. Min Act: -0.0000

Data Index: 258714 (C4 (Web Text))

Max Activating Token Index: 410