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

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

Neuron 625 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: 0.7657. Min Range: -0.7657

Max Act: 0.7578. Min Act: -0.0002

Data Index: 896621 (C4 (Web Text))

Max Activating Token Index: 927

Text #1

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.7565. Min Act: -0.0002

Data Index: 540417 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.7657. Min Act: -0.0002

Data Index: 283164 (C4 (Web Text))

Max Activating Token Index: 342

Text #3

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.7304. Min Act: -0.0002

Data Index: 285726 (C4 (Web Text))

Max Activating Token Index: 372

Text #4

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.7451. Min Act: -0.0002

Data Index: 144230 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.7276. Min Act: -0.0002

Data Index: 1248352 (C4 (Web Text))

Max Activating Token Index: 796

Text #6

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.7307. Min Act: -0.0003

Data Index: 318447 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.7273. Min Act: -0.0002

Data Index: 1338261 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.7222. Min Act: -0.0003

Data Index: 1052493 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.7230. Min Act: -0.0003

Data Index: 1115068 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.7145. Min Act: -0.0002

Data Index: 452639 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.7051. Min Act: -0.0002

Data Index: 307008 (C4 (Web Text))

Max Activating Token Index: 758

Text #12

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.6936. Min Act: -0.0002

Data Index: 627887 (C4 (Web Text))

Max Activating Token Index: 593

Text #13

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.6814. Min Act: -0.0002

Data Index: 308783 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.6660. Min Act: -0.0003

Data Index: 480623 (C4 (Web Text))

Max Activating Token Index: 842

Text #15

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.6880. Min Act: -0.0002

Data Index: 832236 (C4 (Web Text))

Max Activating Token Index: 271

Text #16

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.6710. Min Act: -0.0002

Data Index: 66173 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.6548. Min Act: -0.0002

Data Index: 544166 (C4 (Web Text))

Max Activating Token Index: 632

Text #18

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.6522. Min Act: -0.0003

Data Index: 1183712 (C4 (Web Text))

Max Activating Token Index: 380

Text #19

Max Range: 0.7657. Min Range: -0.7657

Max Act: 0.6374. Min Act: -0.0002

Data Index: 1228634 (C4 (Web Text))

Max Activating Token Index: 882