Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 609 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.2159. Min Act: -0.0001

Data Index: 889121 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1929. Min Act: -0.0001

Data Index: 1273728 (C4 (Web Text))

Max Activating Token Index: 704

Text #2

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1818. Min Act: -0.0001

Data Index: 500391 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1869. Min Act: -0.0001

Data Index: 374603 (C4 (Web Text))

Max Activating Token Index: 61

Text #4

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.2002. Min Act: -0.0001

Data Index: 628056 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1813. Min Act: -0.0001

Data Index: 287143 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1739. Min Act: -0.0001

Data Index: 1024345 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1789. Min Act: -0.0001

Data Index: 1035666 (C4 (Web Text))

Max Activating Token Index: 92

Text #8

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1673. Min Act: -0.0001

Data Index: 889302 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1650. Min Act: -0.0001

Data Index: 728075 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1529. Min Act: -0.0001

Data Index: 1271278 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1508. Min Act: -0.0001

Data Index: 407703 (C4 (Web Text))

Max Activating Token Index: 296

Text #12

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1443. Min Act: -0.0001

Data Index: 70292 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1493. Min Act: -0.0001

Data Index: 327873 (C4 (Web Text))

Max Activating Token Index: 553

Text #14

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1533. Min Act: -0.0001

Data Index: 1060254 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1630. Min Act: -0.0001

Data Index: 909723 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1467. Min Act: -0.0001

Data Index: 1125390 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1630. Min Act: -0.0001

Data Index: 598058 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1466. Min Act: -0.0001

Data Index: 667691 (C4 (Web Text))

Max Activating Token Index: 306

Text #19

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1554. Min Act: -0.0001

Data Index: 68968 (C4 (Web Text))

Max Activating Token Index: 10