Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6010 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.1736. Min Range: -3.1736

Max Act: 3.1736. Min Act: -0.0000

Data Index: 824030 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 3.1736. Min Range: -3.1736

Max Act: 2.7264. Min Act: -0.0000

Data Index: 883203 (C4 (Web Text))

Max Activating Token Index: 906

Text #2

Max Range: 3.1736. Min Range: -3.1736

Max Act: 2.6499. Min Act: -0.0000

Data Index: 117291 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 3.1736. Min Range: -3.1736

Max Act: 2.7298. Min Act: -0.0000

Data Index: 1358772 (C4 (Web Text))

Max Activating Token Index: 599

Text #4

Max Range: 3.1736. Min Range: -3.1736

Max Act: 2.8575. Min Act: -0.0000

Data Index: 605062 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 3.1736. Min Range: -3.1736

Max Act: 2.5601. Min Act: -0.0000

Data Index: 112111 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 3.1736. Min Range: -3.1736

Max Act: 2.6547. Min Act: -0.0000

Data Index: 469103 (C4 (Web Text))

Max Activating Token Index: 181

Text #7

Max Range: 3.1736. Min Range: -3.1736

Max Act: 2.4858. Min Act: -0.0000

Data Index: 575241 (C4 (Web Text))

Max Activating Token Index: 916

Text #8

Max Range: 3.1736. Min Range: -3.1736

Max Act: 2.4665. Min Act: -0.0000

Data Index: 144526 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 3.1736. Min Range: -3.1736

Max Act: 2.4587. Min Act: -0.0000

Data Index: 79814 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 3.1736. Min Range: -3.1736

Max Act: 2.1360. Min Act: -0.0000

Data Index: 1177896 (C4 (Web Text))

Max Activating Token Index: 433

Text #11

Max Range: 3.1736. Min Range: -3.1736

Max Act: 2.4450. Min Act: -0.0000

Data Index: 1336307 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 3.1736. Min Range: -3.1736

Max Act: 2.3423. Min Act: -0.0000

Data Index: 173007 (C4 (Web Text))

Max Activating Token Index: 419

Text #13

Max Range: 3.1736. Min Range: -3.1736

Max Act: 2.3169. Min Act: -0.0000

Data Index: 203205 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 3.1736. Min Range: -3.1736

Max Act: 2.3217. Min Act: -0.0000

Data Index: 594407 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 3.1736. Min Range: -3.1736

Max Act: 2.3094. Min Act: -0.0000

Data Index: 173227 (C4 (Web Text))

Max Activating Token Index: 619

Text #16

Max Range: 3.1736. Min Range: -3.1736

Max Act: 2.2563. Min Act: -0.0000

Data Index: 340179 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 3.1736. Min Range: -3.1736

Max Act: 2.4187. Min Act: -0.0000

Data Index: 1177225 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 3.1736. Min Range: -3.1736

Max Act: 2.2679. Min Act: -0.0000

Data Index: 266001 (C4 (Web Text))

Max Activating Token Index: 521

Text #19

Max Range: 3.1736. Min Range: -3.1736

Max Act: 2.1914. Min Act: -0.0000

Data Index: 1167002 (C4 (Web Text))

Max Activating Token Index: 822