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

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

Neuron 4741 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.6213. Min Act: -0.0001

Data Index: 474523 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.5942. Min Act: -0.0001

Data Index: 254671 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.5734. Min Act: -0.0001

Data Index: 701457 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.5718. Min Act: -0.0001

Data Index: 1207626 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.5580. Min Act: -0.0001

Data Index: 1120648 (C4 (Web Text))

Max Activating Token Index: 1012

Text #5

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.5464. Min Act: -0.0001

Data Index: 41714 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.6152. Min Act: -0.0001

Data Index: 897310 (C4 (Web Text))

Max Activating Token Index: 698

Text #7

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.5535. Min Act: -0.0001

Data Index: 730517 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.5943. Min Act: -0.0001

Data Index: 482790 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.4916. Min Act: -0.0001

Data Index: 848909 (C4 (Web Text))

Max Activating Token Index: 718

Text #10

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.5364. Min Act: -0.0001

Data Index: 89801 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.5129. Min Act: -0.0001

Data Index: 678927 (C4 (Web Text))

Max Activating Token Index: 481

Text #12

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.5138. Min Act: -0.0001

Data Index: 571376 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.5602. Min Act: -0.0001

Data Index: 1316323 (C4 (Web Text))

Max Activating Token Index: 530

Text #14

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.5348. Min Act: -0.0001

Data Index: 1030769 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.5206. Min Act: -0.0001

Data Index: 908942 (C4 (Web Text))

Max Activating Token Index: 515

Text #16

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.5353. Min Act: -0.0001

Data Index: 1140884 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.5810. Min Act: -0.0001

Data Index: 87305 (C4 (Web Text))

Max Activating Token Index: 937

Text #18

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.5147. Min Act: -0.0001

Data Index: 67497 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 0.6213. Min Range: -0.6213

Max Act: 0.4941. Min Act: -0.0001

Data Index: 1041834 (C4 (Web Text))

Max Activating Token Index: 407