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

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

Neuron 3211 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.9931. Min Range: -0.9931

Max Act: 0.9931. Min Act: -0.0002

Data Index: 780987 (C4 (Web Text))

Max Activating Token Index: 274

Text #1

Max Range: 0.9931. Min Range: -0.9931

Max Act: 0.9366. Min Act: -0.0002

Data Index: 783100 (C4 (Web Text))

Max Activating Token Index: 799

Text #2

Max Range: 0.9931. Min Range: -0.9931

Max Act: 0.9595. Min Act: -0.0002

Data Index: 578124 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 0.9931. Min Range: -0.9931

Max Act: 0.9572. Min Act: -0.0002

Data Index: 1323476 (C4 (Web Text))

Max Activating Token Index: 408

Text #4

Max Range: 0.9931. Min Range: -0.9931

Max Act: 0.9225. Min Act: -0.0002

Data Index: 76966 (C4 (Web Text))

Max Activating Token Index: 797

Text #5

Max Range: 0.9931. Min Range: -0.9931

Max Act: 0.9119. Min Act: -0.0002

Data Index: 947099 (C4 (Web Text))

Max Activating Token Index: 956

Text #6

Max Range: 0.9931. Min Range: -0.9931

Max Act: 0.9353. Min Act: -0.0002

Data Index: 39236 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 0.9931. Min Range: -0.9931

Max Act: 0.9131. Min Act: -0.0002

Data Index: 1122550 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 0.9931. Min Range: -0.9931

Max Act: 0.9235. Min Act: -0.0002

Data Index: 1156399 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 0.9931. Min Range: -0.9931

Max Act: 0.9159. Min Act: -0.0002

Data Index: 758634 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 0.9931. Min Range: -0.9931

Max Act: 0.8887. Min Act: -0.0002

Data Index: 968238 (C4 (Web Text))

Max Activating Token Index: 756

Text #11

Max Range: 0.9931. Min Range: -0.9931

Max Act: 0.8984. Min Act: -0.0002

Data Index: 1075807 (C4 (Web Text))

Max Activating Token Index: 75

Text #12

Max Range: 0.9931. Min Range: -0.9931

Max Act: 0.8824. Min Act: -0.0002

Data Index: 1044470 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 0.9931. Min Range: -0.9931

Max Act: 0.8822. Min Act: -0.0002

Data Index: 1076026 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 0.9931. Min Range: -0.9931

Max Act: 0.8879. Min Act: -0.0002

Data Index: 1087645 (C4 (Web Text))

Max Activating Token Index: 369

Text #15

Max Range: 0.9931. Min Range: -0.9931

Max Act: 0.8833. Min Act: -0.0002

Data Index: 55343 (C4 (Web Text))

Max Activating Token Index: 566

Text #16

Max Range: 0.9931. Min Range: -0.9931

Max Act: 0.8832. Min Act: -0.0002

Data Index: 810537 (C4 (Web Text))

Max Activating Token Index: 758

Text #17

Max Range: 0.9931. Min Range: -0.9931

Max Act: 0.8839. Min Act: -0.0002

Data Index: 202019 (C4 (Web Text))

Max Activating Token Index: 456

Text #18

Max Range: 0.9931. Min Range: -0.9931

Max Act: 0.8746. Min Act: -0.0002

Data Index: 251272 (C4 (Web Text))

Max Activating Token Index: 714

Text #19

Max Range: 0.9931. Min Range: -0.9931

Max Act: 0.8762. Min Act: -0.0002

Data Index: 44503 (C4 (Web Text))

Max Activating Token Index: 1014