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

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

Neuron 3898 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2706. Min Range: -2.2706

Max Act: 2.2706. Min Act: -0.0000

Data Index: 1277848 (C4 (Web Text))

Max Activating Token Index: 933

Text #1

Max Range: 2.2706. Min Range: -2.2706

Max Act: 2.1161. Min Act: -0.0000

Data Index: 202840 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 2.2706. Min Range: -2.2706

Max Act: 2.0216. Min Act: -0.0000

Data Index: 155693 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 2.2706. Min Range: -2.2706

Max Act: 2.1417. Min Act: -0.0000

Data Index: 468511 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 2.2706. Min Range: -2.2706

Max Act: 2.0279. Min Act: -0.0000

Data Index: 571621 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 2.2706. Min Range: -2.2706

Max Act: 2.0082. Min Act: -0.0000

Data Index: 476414 (C4 (Web Text))

Max Activating Token Index: 569

Text #6

Max Range: 2.2706. Min Range: -2.2706

Max Act: 1.9621. Min Act: -0.0000

Data Index: 372058 (C4 (Web Text))

Max Activating Token Index: 437

Text #7

Max Range: 2.2706. Min Range: -2.2706

Max Act: 1.9403. Min Act: -0.0000

Data Index: 701136 (C4 (Web Text))

Max Activating Token Index: 734

Text #8

Max Range: 2.2706. Min Range: -2.2706

Max Act: 1.9083. Min Act: -0.0000

Data Index: 301840 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 2.2706. Min Range: -2.2706

Max Act: 1.8649. Min Act: -0.0000

Data Index: 1263931 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 2.2706. Min Range: -2.2706

Max Act: 1.8710. Min Act: -0.0000

Data Index: 863204 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 2.2706. Min Range: -2.2706

Max Act: 1.8586. Min Act: -0.0000

Data Index: 178371 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 2.2706. Min Range: -2.2706

Max Act: 1.8502. Min Act: -0.0000

Data Index: 531104 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 2.2706. Min Range: -2.2706

Max Act: 1.8450. Min Act: -0.0000

Data Index: 123885 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 2.2706. Min Range: -2.2706

Max Act: 1.7131. Min Act: -0.0000

Data Index: 439335 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 2.2706. Min Range: -2.2706

Max Act: 1.7569. Min Act: -0.0000

Data Index: 1303782 (C4 (Web Text))

Max Activating Token Index: 864

Text #16

Max Range: 2.2706. Min Range: -2.2706

Max Act: 1.7494. Min Act: -0.0000

Data Index: 475416 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 2.2706. Min Range: -2.2706

Max Act: 1.8353. Min Act: -0.0000

Data Index: 1105223 (C4 (Web Text))

Max Activating Token Index: 912

Text #18

Max Range: 2.2706. Min Range: -2.2706

Max Act: 1.7304. Min Act: -0.0000

Data Index: 338817 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 2.2706. Min Range: -2.2706

Max Act: 1.6266. Min Act: -0.0000

Data Index: 346681 (C4 (Web Text))

Max Activating Token Index: 221