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

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

Neuron 3685 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6633. Min Range: -0.6633

Max Act: 0.6633. Min Act: -0.0000

Data Index: 63102 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 0.6633. Min Range: -0.6633

Max Act: 0.5773. Min Act: -0.0001

Data Index: 396265 (C4 (Web Text))

Max Activating Token Index: 605

Text #2

Max Range: 0.6633. Min Range: -0.6633

Max Act: 0.5570. Min Act: -0.0000

Data Index: 746294 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 0.6633. Min Range: -0.6633

Max Act: 0.5652. Min Act: -0.0001

Data Index: 1201971 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 0.6633. Min Range: -0.6633

Max Act: 0.4956. Min Act: -0.0000

Data Index: 445254 (C4 (Web Text))

Max Activating Token Index: 242

Text #5

Max Range: 0.6633. Min Range: -0.6633

Max Act: 0.5494. Min Act: -0.0000

Data Index: 676382 (C4 (Web Text))

Max Activating Token Index: 133

Text #6

Max Range: 0.6633. Min Range: -0.6633

Max Act: 0.5137. Min Act: -0.0000

Data Index: 25696 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 0.6633. Min Range: -0.6633

Max Act: 0.5174. Min Act: -0.0000

Data Index: 1158840 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 0.6633. Min Range: -0.6633

Max Act: 0.4917. Min Act: -0.0000

Data Index: 597271 (C4 (Web Text))

Max Activating Token Index: 278

Text #9

Max Range: 0.6633. Min Range: -0.6633

Max Act: 0.4883. Min Act: -0.0000

Data Index: 753842 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 0.6633. Min Range: -0.6633

Max Act: 0.4560. Min Act: -0.0000

Data Index: 1027407 (C4 (Web Text))

Max Activating Token Index: 958

Text #11

Max Range: 0.6633. Min Range: -0.6633

Max Act: 0.4058. Min Act: -0.0000

Data Index: 893630 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 0.6633. Min Range: -0.6633

Max Act: 0.4472. Min Act: -0.0000

Data Index: 1044929 (C4 (Web Text))

Max Activating Token Index: 152

Text #13

Max Range: 0.6633. Min Range: -0.6633

Max Act: 0.4640. Min Act: -0.0000

Data Index: 1072303 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 0.6633. Min Range: -0.6633

Max Act: 0.4572. Min Act: -0.0001

Data Index: 878938 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 0.6633. Min Range: -0.6633

Max Act: 0.4093. Min Act: -0.0001

Data Index: 951245 (C4 (Web Text))

Max Activating Token Index: 481

Text #16

Max Range: 0.6633. Min Range: -0.6633

Max Act: 0.4218. Min Act: -0.0000

Data Index: 891834 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 0.6633. Min Range: -0.6633

Max Act: 0.4149. Min Act: -0.0000

Data Index: 299951 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 0.6633. Min Range: -0.6633

Max Act: 0.4219. Min Act: -0.0000

Data Index: 961394 (C4 (Web Text))

Max Activating Token Index: 550

Text #19

Max Range: 0.6633. Min Range: -0.6633

Max Act: 0.4215. Min Act: -0.0000

Data Index: 1247251 (C4 (Web Text))

Max Activating Token Index: 327