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

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

Neuron 1459 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: 3.0153. Min Range: -3.0153

Max Act: 3.0153. Min Act: -0.0001

Data Index: 133550 (C4 (Web Text))

Max Activating Token Index: 202

Text #1

Max Range: 3.0153. Min Range: -3.0153

Max Act: 2.2834. Min Act: -0.0000

Data Index: 626994 (C4 (Web Text))

Max Activating Token Index: 554

Text #2

Max Range: 3.0153. Min Range: -3.0153

Max Act: 1.9644. Min Act: -0.0001

Data Index: 321891 (C4 (Web Text))

Max Activating Token Index: 296

Text #3

Max Range: 3.0153. Min Range: -3.0153

Max Act: 2.0412. Min Act: -0.0001

Data Index: 336016 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 3.0153. Min Range: -3.0153

Max Act: 1.8693. Min Act: -0.0001

Data Index: 261745 (C4 (Web Text))

Max Activating Token Index: 428

Text #5

Max Range: 3.0153. Min Range: -3.0153

Max Act: 1.8755. Min Act: -0.0001

Data Index: 525201 (C4 (Web Text))

Max Activating Token Index: 733

Text #6

Max Range: 3.0153. Min Range: -3.0153

Max Act: 1.8552. Min Act: -0.0000

Data Index: 199521 (C4 (Web Text))

Max Activating Token Index: 225

Text #7

Max Range: 3.0153. Min Range: -3.0153

Max Act: 1.8527. Min Act: -0.0001

Data Index: 387577 (C4 (Web Text))

Max Activating Token Index: 660

Text #8

Max Range: 3.0153. Min Range: -3.0153

Max Act: 1.7983. Min Act: -0.0000

Data Index: 517650 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 3.0153. Min Range: -3.0153

Max Act: 1.8119. Min Act: -0.0001

Data Index: 716971 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 3.0153. Min Range: -3.0153

Max Act: 1.5475. Min Act: -0.0001

Data Index: 586256 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 3.0153. Min Range: -3.0153

Max Act: 1.7301. Min Act: -0.0001

Data Index: 483502 (C4 (Web Text))

Max Activating Token Index: 970

Text #12

Max Range: 3.0153. Min Range: -3.0153

Max Act: 1.5995. Min Act: -0.0001

Data Index: 1083445 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 3.0153. Min Range: -3.0153

Max Act: 1.4962. Min Act: -0.0001

Data Index: 580394 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 3.0153. Min Range: -3.0153

Max Act: 1.5690. Min Act: -0.0000

Data Index: 1243544 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 3.0153. Min Range: -3.0153

Max Act: 1.5082. Min Act: -0.0000

Data Index: 1279358 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 3.0153. Min Range: -3.0153

Max Act: 1.5127. Min Act: -0.0000

Data Index: 1339166 (C4 (Web Text))

Max Activating Token Index: 442

Text #17

Max Range: 3.0153. Min Range: -3.0153

Max Act: 1.5105. Min Act: -0.0001

Data Index: 274673 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 3.0153. Min Range: -3.0153

Max Act: 1.5148. Min Act: -0.0001

Data Index: 502250 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 3.0153. Min Range: -3.0153

Max Act: 1.4610. Min Act: -0.0001

Data Index: 966604 (C4 (Web Text))

Max Activating Token Index: 411