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

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

Neuron 2211 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2571. Min Range: -4.2571

Max Act: 3.9081. Min Act: -0.0001

Data Index: 607857 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 4.2571. Min Range: -4.2571

Max Act: 3.9470. Min Act: -0.0001

Data Index: 493392 (C4 (Web Text))

Max Activating Token Index: 177

Text #2

Max Range: 4.2571. Min Range: -4.2571

Max Act: 3.7548. Min Act: -0.0001

Data Index: 629850 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 4.2571. Min Range: -4.2571

Max Act: 4.2571. Min Act: -0.0001

Data Index: 330650 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 4.2571. Min Range: -4.2571

Max Act: 3.9222. Min Act: -0.0000

Data Index: 1239536 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 4.2571. Min Range: -4.2571

Max Act: 3.9052. Min Act: -0.0000

Data Index: 1078016 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 4.2571. Min Range: -4.2571

Max Act: 3.8867. Min Act: -0.0001

Data Index: 1105423 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 4.2571. Min Range: -4.2571

Max Act: 3.5880. Min Act: -0.0001

Data Index: 1335340 (C4 (Web Text))

Max Activating Token Index: 802

Text #8

Max Range: 4.2571. Min Range: -4.2571

Max Act: 3.7472. Min Act: -0.0001

Data Index: 349567 (C4 (Web Text))

Max Activating Token Index: 813

Text #9

Max Range: 4.2571. Min Range: -4.2571

Max Act: 3.7520. Min Act: -0.0001

Data Index: 1202858 (C4 (Web Text))

Max Activating Token Index: 1004

Text #10

Max Range: 4.2571. Min Range: -4.2571

Max Act: 3.6249. Min Act: -0.0001

Data Index: 643987 (C4 (Web Text))

Max Activating Token Index: 324

Text #11

Max Range: 4.2571. Min Range: -4.2571

Max Act: 3.6050. Min Act: -0.0001

Data Index: 1303162 (C4 (Web Text))

Max Activating Token Index: 417

Text #12

Max Range: 4.2571. Min Range: -4.2571

Max Act: 3.7694. Min Act: -0.0001

Data Index: 1091140 (C4 (Web Text))

Max Activating Token Index: 647

Text #13

Max Range: 4.2571. Min Range: -4.2571

Max Act: 3.5879. Min Act: -0.0001

Data Index: 970585 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 4.2571. Min Range: -4.2571

Max Act: 3.4580. Min Act: -0.0001

Data Index: 758734 (C4 (Web Text))

Max Activating Token Index: 940

Text #15

Max Range: 4.2571. Min Range: -4.2571

Max Act: 3.2899. Min Act: -0.0001

Data Index: 713569 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 4.2571. Min Range: -4.2571

Max Act: 3.1757. Min Act: -0.0001

Data Index: 332733 (C4 (Web Text))

Max Activating Token Index: 193

Text #17

Max Range: 4.2571. Min Range: -4.2571

Max Act: 3.4710. Min Act: -0.0001

Data Index: 140952 (C4 (Web Text))

Max Activating Token Index: 246

Text #18

Max Range: 4.2571. Min Range: -4.2571

Max Act: 3.6068. Min Act: -0.0000

Data Index: 1314365 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 4.2571. Min Range: -4.2571

Max Act: 3.1452. Min Act: -0.0001

Data Index: 653020 (C4 (Web Text))

Max Activating Token Index: 422