Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1929 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.0659. Min Range: -1.0659

Max Act: 1.0659. Min Act: -0.0001

Data Index: 366995 (C4 (Web Text))

Max Activating Token Index: 977

Text #1

Max Range: 1.0659. Min Range: -1.0659

Max Act: 1.0145. Min Act: -0.0001

Data Index: 997700 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.9331. Min Act: -0.0001

Data Index: 458653 (C4 (Web Text))

Max Activating Token Index: 905

Text #3

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.8842. Min Act: -0.0001

Data Index: 799018 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.8699. Min Act: -0.0001

Data Index: 508049 (C4 (Web Text))

Max Activating Token Index: 992

Text #5

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.8970. Min Act: -0.0001

Data Index: 467295 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.8693. Min Act: -0.0001

Data Index: 422263 (C4 (Web Text))

Max Activating Token Index: 836

Text #7

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.8696. Min Act: -0.0001

Data Index: 452543 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.8309. Min Act: -0.0001

Data Index: 596205 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.8475. Min Act: -0.0001

Data Index: 763278 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.8459. Min Act: -0.0001

Data Index: 340318 (C4 (Web Text))

Max Activating Token Index: 591

Text #11

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.7999. Min Act: -0.0001

Data Index: 478207 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.8162. Min Act: -0.0001

Data Index: 860342 (C4 (Web Text))

Max Activating Token Index: 260

Text #13

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.8956. Min Act: -0.0001

Data Index: 921087 (C4 (Web Text))

Max Activating Token Index: 736

Text #14

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.8157. Min Act: -0.0001

Data Index: 137278 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.8436. Min Act: -0.0001

Data Index: 773473 (C4 (Web Text))

Max Activating Token Index: 336

Text #16

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.8115. Min Act: -0.0001

Data Index: 733715 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.8301. Min Act: -0.0001

Data Index: 104555 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.8728. Min Act: -0.0001

Data Index: 201963 (C4 (Web Text))

Max Activating Token Index: 884

Text #19

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.7862. Min Act: -0.0001

Data Index: 917686 (C4 (Web Text))

Max Activating Token Index: 357