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

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

Neuron 4719 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.7688. Min Act: -0.0001

Data Index: 1308215 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.7061. Min Act: -0.0001

Data Index: 1222412 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.8720. Min Act: -0.0001

Data Index: 477583 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.7312. Min Act: -0.0001

Data Index: 890630 (C4 (Web Text))

Max Activating Token Index: 314

Text #4

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.7167. Min Act: -0.0001

Data Index: 133139 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.7518. Min Act: -0.0001

Data Index: 1449485 (Python Code)

Max Activating Token Index: 282

Text #6

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.7033. Min Act: -0.0001

Data Index: 863847 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.6624. Min Act: -0.0001

Data Index: 855328 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.6328. Min Act: -0.0001

Data Index: 596636 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.7224. Min Act: -0.0001

Data Index: 69291 (C4 (Web Text))

Max Activating Token Index: 438

Text #10

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.7828. Min Act: -0.0001

Data Index: 1014940 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.6982. Min Act: -0.0001

Data Index: 1048130 (C4 (Web Text))

Max Activating Token Index: 642

Text #12

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.7183. Min Act: -0.0001

Data Index: 1013164 (C4 (Web Text))

Max Activating Token Index: 748

Text #13

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.7585. Min Act: -0.0001

Data Index: 845115 (C4 (Web Text))

Max Activating Token Index: 630

Text #14

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.7064. Min Act: -0.0001

Data Index: 377935 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.6875. Min Act: -0.0001

Data Index: 425827 (C4 (Web Text))

Max Activating Token Index: 668

Text #16

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.7696. Min Act: -0.0001

Data Index: 1291967 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.6946. Min Act: -0.0001

Data Index: 312831 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.6586. Min Act: -0.0001

Data Index: 1320548 (C4 (Web Text))

Max Activating Token Index: 966

Text #19

Max Range: 0.8720. Min Range: -0.8720

Max Act: 0.6571. Min Act: -0.0001

Data Index: 203218 (C4 (Web Text))

Max Activating Token Index: 813