Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3241 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9424. Min Range: -0.9424

Max Act: 0.9424. Min Act: -0.0001

Data Index: 558313 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 0.9424. Min Range: -0.9424

Max Act: 0.9036. Min Act: -0.0001

Data Index: 12425 (C4 (Web Text))

Max Activating Token Index: 464

Text #2

Max Range: 0.9424. Min Range: -0.9424

Max Act: 0.9290. Min Act: -0.0001

Data Index: 717916 (C4 (Web Text))

Max Activating Token Index: 843

Text #3

Max Range: 0.9424. Min Range: -0.9424

Max Act: 0.8972. Min Act: -0.0001

Data Index: 420511 (C4 (Web Text))

Max Activating Token Index: 321

Text #4

Max Range: 0.9424. Min Range: -0.9424

Max Act: 0.8742. Min Act: -0.0001

Data Index: 414786 (C4 (Web Text))

Max Activating Token Index: 509

Text #5

Max Range: 0.9424. Min Range: -0.9424

Max Act: 0.7925. Min Act: -0.0001

Data Index: 12272 (C4 (Web Text))

Max Activating Token Index: 217

Text #6

Max Range: 0.9424. Min Range: -0.9424

Max Act: 0.8030. Min Act: -0.0001

Data Index: 516891 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 0.9424. Min Range: -0.9424

Max Act: 0.7942. Min Act: -0.0001

Data Index: 209019 (C4 (Web Text))

Max Activating Token Index: 519

Text #8

Max Range: 0.9424. Min Range: -0.9424

Max Act: 0.8406. Min Act: -0.0001

Data Index: 716099 (C4 (Web Text))

Max Activating Token Index: 133

Text #9

Max Range: 0.9424. Min Range: -0.9424

Max Act: 0.7422. Min Act: -0.0001

Data Index: 234227 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 0.9424. Min Range: -0.9424

Max Act: 0.8335. Min Act: -0.0001

Data Index: 590444 (C4 (Web Text))

Max Activating Token Index: 955

Text #11

Max Range: 0.9424. Min Range: -0.9424

Max Act: 0.7741. Min Act: -0.0001

Data Index: 25862 (C4 (Web Text))

Max Activating Token Index: 110

Text #12

Max Range: 0.9424. Min Range: -0.9424

Max Act: 0.7695. Min Act: -0.0001

Data Index: 47123 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 0.9424. Min Range: -0.9424

Max Act: 0.7387. Min Act: -0.0001

Data Index: 597532 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 0.9424. Min Range: -0.9424

Max Act: 0.7649. Min Act: -0.0001

Data Index: 431119 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 0.9424. Min Range: -0.9424

Max Act: 0.7644. Min Act: -0.0001

Data Index: 1262420 (C4 (Web Text))

Max Activating Token Index: 933

Text #16

Max Range: 0.9424. Min Range: -0.9424

Max Act: 0.7871. Min Act: -0.0001

Data Index: 974286 (C4 (Web Text))

Max Activating Token Index: 458

Text #17

Max Range: 0.9424. Min Range: -0.9424

Max Act: 0.7035. Min Act: -0.0001

Data Index: 227346 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 0.9424. Min Range: -0.9424

Max Act: 0.7527. Min Act: -0.0001

Data Index: 1121009 (C4 (Web Text))

Max Activating Token Index: 287

Text #19

Max Range: 0.9424. Min Range: -0.9424

Max Act: 0.7534. Min Act: -0.0001

Data Index: 1052471 (C4 (Web Text))

Max Activating Token Index: 340