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

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

Neuron 817 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5823. Min Range: -0.5823

Max Act: 0.5823. Min Act: -0.0000

Data Index: 1341138 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 0.5823. Min Range: -0.5823

Max Act: 0.5728. Min Act: -0.0001

Data Index: 229343 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 0.5823. Min Range: -0.5823

Max Act: 0.5505. Min Act: -0.0001

Data Index: 204142 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 0.5823. Min Range: -0.5823

Max Act: 0.5210. Min Act: -0.0001

Data Index: 313700 (C4 (Web Text))

Max Activating Token Index: 915

Text #4

Max Range: 0.5823. Min Range: -0.5823

Max Act: 0.4974. Min Act: -0.0001

Data Index: 256353 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 0.5823. Min Range: -0.5823

Max Act: 0.4980. Min Act: -0.0001

Data Index: 1138423 (C4 (Web Text))

Max Activating Token Index: 170

Text #6

Max Range: 0.5823. Min Range: -0.5823

Max Act: 0.5061. Min Act: -0.0001

Data Index: 826430 (C4 (Web Text))

Max Activating Token Index: 257

Text #7

Max Range: 0.5823. Min Range: -0.5823

Max Act: 0.4738. Min Act: -0.0001

Data Index: 948793 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 0.5823. Min Range: -0.5823

Max Act: 0.4820. Min Act: -0.0001

Data Index: 863155 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 0.5823. Min Range: -0.5823

Max Act: 0.4744. Min Act: -0.0001

Data Index: 609748 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 0.5823. Min Range: -0.5823

Max Act: 0.4414. Min Act: -0.0001

Data Index: 163357 (C4 (Web Text))

Max Activating Token Index: 900

Text #11

Max Range: 0.5823. Min Range: -0.5823

Max Act: 0.4521. Min Act: -0.0001

Data Index: 159540 (C4 (Web Text))

Max Activating Token Index: 3

Text #12

Max Range: 0.5823. Min Range: -0.5823

Max Act: 0.4438. Min Act: -0.0001

Data Index: 93468 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 0.5823. Min Range: -0.5823

Max Act: 0.4419. Min Act: -0.0001

Data Index: 411445 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 0.5823. Min Range: -0.5823

Max Act: 0.4394. Min Act: -0.0000

Data Index: 302386 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 0.5823. Min Range: -0.5823

Max Act: 0.4340. Min Act: -0.0001

Data Index: 1056916 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 0.5823. Min Range: -0.5823

Max Act: 0.4193. Min Act: -0.0001

Data Index: 597279 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 0.5823. Min Range: -0.5823

Max Act: 0.4329. Min Act: -0.0001

Data Index: 474001 (C4 (Web Text))

Max Activating Token Index: 7

Text #18

Max Range: 0.5823. Min Range: -0.5823

Max Act: 0.4120. Min Act: -0.0001

Data Index: 542635 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 0.5823. Min Range: -0.5823

Max Act: 0.4082. Min Act: -0.0001

Data Index: 224314 (C4 (Web Text))

Max Activating Token Index: 968