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

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

Neuron 1770 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5741. Min Range: -1.5741

Max Act: 1.5741. Min Act: -0.0000

Data Index: 1359594 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 1.5741. Min Range: -1.5741

Max Act: 1.5155. Min Act: -0.0000

Data Index: 1342500 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 1.5741. Min Range: -1.5741

Max Act: 1.5048. Min Act: -0.0000

Data Index: 802493 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 1.5741. Min Range: -1.5741

Max Act: 1.4796. Min Act: -0.0000

Data Index: 616684 (C4 (Web Text))

Max Activating Token Index: 338

Text #4

Max Range: 1.5741. Min Range: -1.5741

Max Act: 1.3539. Min Act: -0.0000

Data Index: 1332440 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 1.5741. Min Range: -1.5741

Max Act: 1.3567. Min Act: -0.0000

Data Index: 843359 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 1.5741. Min Range: -1.5741

Max Act: 1.2936. Min Act: -0.0000

Data Index: 2482 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 1.5741. Min Range: -1.5741

Max Act: 1.2334. Min Act: -0.0000

Data Index: 860756 (C4 (Web Text))

Max Activating Token Index: 857

Text #8

Max Range: 1.5741. Min Range: -1.5741

Max Act: 1.2143. Min Act: -0.0000

Data Index: 348955 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 1.5741. Min Range: -1.5741

Max Act: 1.2158. Min Act: -0.0000

Data Index: 41812 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 1.5741. Min Range: -1.5741

Max Act: 1.1885. Min Act: -0.0000

Data Index: 730236 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 1.5741. Min Range: -1.5741

Max Act: 1.1709. Min Act: -0.0000

Data Index: 98000 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 1.5741. Min Range: -1.5741

Max Act: 1.1939. Min Act: -0.0000

Data Index: 504158 (C4 (Web Text))

Max Activating Token Index: 593

Text #13

Max Range: 1.5741. Min Range: -1.5741

Max Act: 1.1949. Min Act: -0.0000

Data Index: 1178946 (C4 (Web Text))

Max Activating Token Index: 479

Text #14

Max Range: 1.5741. Min Range: -1.5741

Max Act: 1.0513. Min Act: -0.0000

Data Index: 275662 (C4 (Web Text))

Max Activating Token Index: 955

Text #15

Max Range: 1.5741. Min Range: -1.5741

Max Act: 1.1593. Min Act: -0.0000

Data Index: 853805 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 1.5741. Min Range: -1.5741

Max Act: 1.1621. Min Act: -0.0000

Data Index: 498820 (C4 (Web Text))

Max Activating Token Index: 271

Text #17

Max Range: 1.5741. Min Range: -1.5741

Max Act: 1.1538. Min Act: -0.0000

Data Index: 133181 (C4 (Web Text))

Max Activating Token Index: 282

Text #18

Max Range: 1.5741. Min Range: -1.5741

Max Act: 1.1296. Min Act: -0.0000

Data Index: 1152221 (C4 (Web Text))

Max Activating Token Index: 965

Text #19

Max Range: 1.5741. Min Range: -1.5741

Max Act: 1.0981. Min Act: -0.0000

Data Index: 227420 (C4 (Web Text))

Max Activating Token Index: 761