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

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

Neuron 657 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.1145. Min Range: -2.1145

Max Act: 2.1145. Min Act: -0.0001

Data Index: 1128167 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 2.1145. Min Range: -2.1145

Max Act: 1.8033. Min Act: -0.0001

Data Index: 74471 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 2.1145. Min Range: -2.1145

Max Act: 1.6837. Min Act: -0.0001

Data Index: 733611 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 2.1145. Min Range: -2.1145

Max Act: 1.6037. Min Act: -0.0001

Data Index: 379468 (C4 (Web Text))

Max Activating Token Index: 336

Text #4

Max Range: 2.1145. Min Range: -2.1145

Max Act: 1.5916. Min Act: -0.0001

Data Index: 1054692 (C4 (Web Text))

Max Activating Token Index: 479

Text #5

Max Range: 2.1145. Min Range: -2.1145

Max Act: 1.4566. Min Act: -0.0001

Data Index: 852350 (C4 (Web Text))

Max Activating Token Index: 657

Text #6

Max Range: 2.1145. Min Range: -2.1145

Max Act: 1.4490. Min Act: -0.0001

Data Index: 1051202 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 2.1145. Min Range: -2.1145

Max Act: 1.5086. Min Act: -0.0001

Data Index: 833157 (C4 (Web Text))

Max Activating Token Index: 292

Text #8

Max Range: 2.1145. Min Range: -2.1145

Max Act: 1.3308. Min Act: -0.0001

Data Index: 1120923 (C4 (Web Text))

Max Activating Token Index: 538

Text #9

Max Range: 2.1145. Min Range: -2.1145

Max Act: 1.3590. Min Act: -0.0001

Data Index: 169823 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 2.1145. Min Range: -2.1145

Max Act: 1.3476. Min Act: -0.0001

Data Index: 893987 (C4 (Web Text))

Max Activating Token Index: 427

Text #11

Max Range: 2.1145. Min Range: -2.1145

Max Act: 1.3633. Min Act: -0.0001

Data Index: 851253 (C4 (Web Text))

Max Activating Token Index: 580

Text #12

Max Range: 2.1145. Min Range: -2.1145

Max Act: 1.2439. Min Act: -0.0001

Data Index: 1331199 (C4 (Web Text))

Max Activating Token Index: 261

Text #13

Max Range: 2.1145. Min Range: -2.1145

Max Act: 1.2463. Min Act: -0.0001

Data Index: 1300766 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 2.1145. Min Range: -2.1145

Max Act: 1.1915. Min Act: -0.0001

Data Index: 606619 (C4 (Web Text))

Max Activating Token Index: 795

Text #15

Max Range: 2.1145. Min Range: -2.1145

Max Act: 1.0644. Min Act: -0.0001

Data Index: 323549 (C4 (Web Text))

Max Activating Token Index: 909

Text #16

Max Range: 2.1145. Min Range: -2.1145

Max Act: 1.1713. Min Act: -0.0001

Data Index: 1118922 (C4 (Web Text))

Max Activating Token Index: 479

Text #17

Max Range: 2.1145. Min Range: -2.1145

Max Act: 1.0335. Min Act: -0.0001

Data Index: 530142 (C4 (Web Text))

Max Activating Token Index: 645

Text #18

Max Range: 2.1145. Min Range: -2.1145

Max Act: 0.9154. Min Act: -0.0001

Data Index: 497046 (C4 (Web Text))

Max Activating Token Index: 554

Text #19

Max Range: 2.1145. Min Range: -2.1145

Max Act: 1.1241. Min Act: -0.0001

Data Index: 621119 (C4 (Web Text))

Max Activating Token Index: 481