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

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

Neuron 3764 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.4024. Min Range: -4.4024

Max Act: 4.4024. Min Act: -0.0000

Data Index: 1327980 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 4.4024. Min Range: -4.4024

Max Act: 3.7320. Min Act: -0.0000

Data Index: 752483 (C4 (Web Text))

Max Activating Token Index: 597

Text #2

Max Range: 4.4024. Min Range: -4.4024

Max Act: 4.1234. Min Act: -0.0001

Data Index: 499116 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 4.4024. Min Range: -4.4024

Max Act: 3.7536. Min Act: -0.0001

Data Index: 930541 (C4 (Web Text))

Max Activating Token Index: 149

Text #4

Max Range: 4.4024. Min Range: -4.4024

Max Act: 3.1775. Min Act: -0.0001

Data Index: 1310385 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 4.4024. Min Range: -4.4024

Max Act: 2.9280. Min Act: -0.0001

Data Index: 451349 (C4 (Web Text))

Max Activating Token Index: 371

Text #6

Max Range: 4.4024. Min Range: -4.4024

Max Act: 2.9876. Min Act: -0.0001

Data Index: 850698 (C4 (Web Text))

Max Activating Token Index: 966

Text #7

Max Range: 4.4024. Min Range: -4.4024

Max Act: 2.9966. Min Act: -0.0001

Data Index: 707427 (C4 (Web Text))

Max Activating Token Index: 878

Text #8

Max Range: 4.4024. Min Range: -4.4024

Max Act: 2.8975. Min Act: -0.0000

Data Index: 162443 (C4 (Web Text))

Max Activating Token Index: 390

Text #9

Max Range: 4.4024. Min Range: -4.4024

Max Act: 2.6861. Min Act: -0.0000

Data Index: 519508 (C4 (Web Text))

Max Activating Token Index: 619

Text #10

Max Range: 4.4024. Min Range: -4.4024

Max Act: 2.6484. Min Act: -0.0000

Data Index: 335709 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 4.4024. Min Range: -4.4024

Max Act: 2.6295. Min Act: -0.0000

Data Index: 790822 (C4 (Web Text))

Max Activating Token Index: 465

Text #12

Max Range: 4.4024. Min Range: -4.4024

Max Act: 2.6111. Min Act: -0.0001

Data Index: 110581 (C4 (Web Text))

Max Activating Token Index: 190

Text #13

Max Range: 4.4024. Min Range: -4.4024

Max Act: 2.5835. Min Act: -0.0001

Data Index: 963244 (C4 (Web Text))

Max Activating Token Index: 403

Text #14

Max Range: 4.4024. Min Range: -4.4024

Max Act: 2.5617. Min Act: -0.0000

Data Index: 1310528 (C4 (Web Text))

Max Activating Token Index: 392

Text #15

Max Range: 4.4024. Min Range: -4.4024

Max Act: 2.6827. Min Act: -0.0001

Data Index: 260478 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 4.4024. Min Range: -4.4024

Max Act: 2.5366. Min Act: -0.0001

Data Index: 332001 (C4 (Web Text))

Max Activating Token Index: 889

Text #17

Max Range: 4.4024. Min Range: -4.4024

Max Act: 2.6403. Min Act: -0.0001

Data Index: 1314178 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 4.4024. Min Range: -4.4024

Max Act: 2.5142. Min Act: -0.0000

Data Index: 897592 (C4 (Web Text))

Max Activating Token Index: 505

Text #19

Max Range: 4.4024. Min Range: -4.4024

Max Act: 2.6085. Min Act: -0.0001

Data Index: 530898 (C4 (Web Text))

Max Activating Token Index: 731