Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3104 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2442. Min Range: -1.2442

Max Act: 1.2442. Min Act: -0.0001

Data Index: 967819 (C4 (Web Text))

Max Activating Token Index: 1011

Text #1

Max Range: 1.2442. Min Range: -1.2442

Max Act: 1.2310. Min Act: -0.0001

Data Index: 294377 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 1.2442. Min Range: -1.2442

Max Act: 1.2098. Min Act: -0.0000

Data Index: 591861 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 1.2442. Min Range: -1.2442

Max Act: 1.1863. Min Act: -0.0000

Data Index: 1096012 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 1.2442. Min Range: -1.2442

Max Act: 1.0708. Min Act: -0.0000

Data Index: 1078594 (C4 (Web Text))

Max Activating Token Index: 259

Text #5

Max Range: 1.2442. Min Range: -1.2442

Max Act: 1.0735. Min Act: -0.0001

Data Index: 998707 (C4 (Web Text))

Max Activating Token Index: 273

Text #6

Max Range: 1.2442. Min Range: -1.2442

Max Act: 1.1225. Min Act: -0.0000

Data Index: 841899 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 1.2442. Min Range: -1.2442

Max Act: 1.0495. Min Act: -0.0000

Data Index: 1213016 (C4 (Web Text))

Max Activating Token Index: 673

Text #8

Max Range: 1.2442. Min Range: -1.2442

Max Act: 1.0428. Min Act: -0.0001

Data Index: 507789 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 1.2442. Min Range: -1.2442

Max Act: 0.9650. Min Act: -0.0000

Data Index: 1216854 (C4 (Web Text))

Max Activating Token Index: 622

Text #10

Max Range: 1.2442. Min Range: -1.2442

Max Act: 1.0049. Min Act: -0.0001

Data Index: 1171535 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 1.2442. Min Range: -1.2442

Max Act: 0.9710. Min Act: -0.0001

Data Index: 1043755 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 1.2442. Min Range: -1.2442

Max Act: 0.9667. Min Act: -0.0000

Data Index: 1047808 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 1.2442. Min Range: -1.2442

Max Act: 0.9336. Min Act: -0.0001

Data Index: 1284140 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 1.2442. Min Range: -1.2442

Max Act: 0.9781. Min Act: -0.0000

Data Index: 913254 (C4 (Web Text))

Max Activating Token Index: 155

Text #15

Max Range: 1.2442. Min Range: -1.2442

Max Act: 0.9502. Min Act: -0.0001

Data Index: 630857 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 1.2442. Min Range: -1.2442

Max Act: 0.9374. Min Act: -0.0000

Data Index: 815827 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 1.2442. Min Range: -1.2442

Max Act: 0.9552. Min Act: -0.0000

Data Index: 153136 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 1.2442. Min Range: -1.2442

Max Act: 0.8802. Min Act: -0.0000

Data Index: 1071785 (C4 (Web Text))

Max Activating Token Index: 210

Text #19

Max Range: 1.2442. Min Range: -1.2442

Max Act: 0.8727. Min Act: -0.0000

Data Index: 250316 (C4 (Web Text))

Max Activating Token Index: 160