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

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

Neuron 4412 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.9209. Min Range: -7.9209

Max Act: 7.9209. Min Act: -0.0000

Data Index: 511518 (C4 (Web Text))

Max Activating Token Index: 983

Text #1

Max Range: 7.9209. Min Range: -7.9209

Max Act: 7.6503. Min Act: -0.0000

Data Index: 978632 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 7.9209. Min Range: -7.9209

Max Act: 6.9003. Min Act: -0.0000

Data Index: 434991 (C4 (Web Text))

Max Activating Token Index: 964

Text #3

Max Range: 7.9209. Min Range: -7.9209

Max Act: 6.6640. Min Act: -0.0000

Data Index: 698394 (C4 (Web Text))

Max Activating Token Index: 582

Text #4

Max Range: 7.9209. Min Range: -7.9209

Max Act: 6.9616. Min Act: -0.0000

Data Index: 22274 (C4 (Web Text))

Max Activating Token Index: 599

Text #5

Max Range: 7.9209. Min Range: -7.9209

Max Act: 6.8991. Min Act: -0.0000

Data Index: 723215 (C4 (Web Text))

Max Activating Token Index: 687

Text #6

Max Range: 7.9209. Min Range: -7.9209

Max Act: 6.9232. Min Act: -0.0000

Data Index: 1016510 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 7.9209. Min Range: -7.9209

Max Act: 6.6802. Min Act: -0.0000

Data Index: 172867 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 7.9209. Min Range: -7.9209

Max Act: 6.6852. Min Act: -0.0000

Data Index: 788104 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 7.9209. Min Range: -7.9209

Max Act: 6.8394. Min Act: -0.0000

Data Index: 580551 (C4 (Web Text))

Max Activating Token Index: 179

Text #10

Max Range: 7.9209. Min Range: -7.9209

Max Act: 6.9488. Min Act: -0.0000

Data Index: 67239 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 7.9209. Min Range: -7.9209

Max Act: 6.6934. Min Act: -0.0000

Data Index: 1090256 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 7.9209. Min Range: -7.9209

Max Act: 6.5062. Min Act: -0.0000

Data Index: 884248 (C4 (Web Text))

Max Activating Token Index: 426

Text #13

Max Range: 7.9209. Min Range: -7.9209

Max Act: 6.6966. Min Act: -0.0000

Data Index: 415476 (C4 (Web Text))

Max Activating Token Index: 662

Text #14

Max Range: 7.9209. Min Range: -7.9209

Max Act: 6.6658. Min Act: -0.0000

Data Index: 1041411 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 7.9209. Min Range: -7.9209

Max Act: 6.4476. Min Act: -0.0000

Data Index: 571656 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 7.9209. Min Range: -7.9209

Max Act: 6.5206. Min Act: -0.0000

Data Index: 1067329 (C4 (Web Text))

Max Activating Token Index: 983

Text #17

Max Range: 7.9209. Min Range: -7.9209

Max Act: 6.3051. Min Act: -0.0000

Data Index: 1075660 (C4 (Web Text))

Max Activating Token Index: 937

Text #18

Max Range: 7.9209. Min Range: -7.9209

Max Act: 6.2060. Min Act: -0.0000

Data Index: 1356709 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 7.9209. Min Range: -7.9209

Max Act: 6.4003. Min Act: -0.0000

Data Index: 1202153 (C4 (Web Text))

Max Activating Token Index: 507