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

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

Neuron 5096 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.7617. Min Act: -0.0000

Data Index: 1076938 (C4 (Web Text))

Max Activating Token Index: 466

Text #1

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.7244. Min Act: -0.0000

Data Index: 609185 (C4 (Web Text))

Max Activating Token Index: 719

Text #2

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.5425. Min Act: -0.0000

Data Index: 1020776 (C4 (Web Text))

Max Activating Token Index: 415

Text #3

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.5222. Min Act: -0.0000

Data Index: 68668 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.4628. Min Act: -0.0000

Data Index: 1276350 (C4 (Web Text))

Max Activating Token Index: 865

Text #5

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.4389. Min Act: -0.0000

Data Index: 227522 (C4 (Web Text))

Max Activating Token Index: 813

Text #6

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.4690. Min Act: -0.0000

Data Index: 846119 (C4 (Web Text))

Max Activating Token Index: 990

Text #7

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.4200. Min Act: -0.0000

Data Index: 419301 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.4525. Min Act: -0.0000

Data Index: 1253506 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.4239. Min Act: -0.0000

Data Index: 643337 (C4 (Web Text))

Max Activating Token Index: 413

Text #10

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.4232. Min Act: -0.0000

Data Index: 701089 (C4 (Web Text))

Max Activating Token Index: 485

Text #11

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.4633. Min Act: -0.0000

Data Index: 65028 (C4 (Web Text))

Max Activating Token Index: 902

Text #12

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.4007. Min Act: -0.0000

Data Index: 290391 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.4281. Min Act: -0.0000

Data Index: 1212846 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.4447. Min Act: -0.0000

Data Index: 1130068 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.4182. Min Act: -0.0000

Data Index: 83180 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.4179. Min Act: -0.0000

Data Index: 467560 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.3907. Min Act: -0.0000

Data Index: 778242 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.4119. Min Act: -0.0000

Data Index: 1214549 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 0.7617. Min Range: -0.7617

Max Act: 0.4066. Min Act: -0.0000

Data Index: 1110287 (C4 (Web Text))

Max Activating Token Index: 466