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

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

Neuron 2 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8814. Min Range: -4.8814

Max Act: 4.8814. Min Act: -0.0000

Data Index: 697417 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 4.8814. Min Range: -4.8814

Max Act: 3.3428. Min Act: -0.0000

Data Index: 560980 (C4 (Web Text))

Max Activating Token Index: 1011

Text #2

Max Range: 4.8814. Min Range: -4.8814

Max Act: 2.8755. Min Act: -0.0000

Data Index: 563263 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 4.8814. Min Range: -4.8814

Max Act: 2.7256. Min Act: -0.0000

Data Index: 471921 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 4.8814. Min Range: -4.8814

Max Act: 2.6168. Min Act: -0.0000

Data Index: 235237 (C4 (Web Text))

Max Activating Token Index: 888

Text #5

Max Range: 4.8814. Min Range: -4.8814

Max Act: 2.4165. Min Act: -0.0000

Data Index: 1262783 (C4 (Web Text))

Max Activating Token Index: 291

Text #6

Max Range: 4.8814. Min Range: -4.8814

Max Act: 2.1642. Min Act: -0.0000

Data Index: 374575 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 4.8814. Min Range: -4.8814

Max Act: 2.3560. Min Act: -0.0000

Data Index: 700823 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 4.8814. Min Range: -4.8814

Max Act: 2.2294. Min Act: -0.0000

Data Index: 546431 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 4.8814. Min Range: -4.8814

Max Act: 2.1531. Min Act: -0.0000

Data Index: 197728 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 4.8814. Min Range: -4.8814

Max Act: 2.0376. Min Act: -0.0000

Data Index: 1129894 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 4.8814. Min Range: -4.8814

Max Act: 2.0116. Min Act: -0.0000

Data Index: 73545 (C4 (Web Text))

Max Activating Token Index: 751

Text #12

Max Range: 4.8814. Min Range: -4.8814

Max Act: 2.2491. Min Act: -0.0000

Data Index: 431560 (C4 (Web Text))

Max Activating Token Index: 812

Text #13

Max Range: 4.8814. Min Range: -4.8814

Max Act: 2.2331. Min Act: -0.0000

Data Index: 639664 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 4.8814. Min Range: -4.8814

Max Act: 2.2120. Min Act: -0.0000

Data Index: 730580 (C4 (Web Text))

Max Activating Token Index: 508

Text #15

Max Range: 4.8814. Min Range: -4.8814

Max Act: 2.0471. Min Act: -0.0000

Data Index: 1349203 (C4 (Web Text))

Max Activating Token Index: 195

Text #16

Max Range: 4.8814. Min Range: -4.8814

Max Act: 1.9039. Min Act: -0.0000

Data Index: 486270 (C4 (Web Text))

Max Activating Token Index: 815

Text #17

Max Range: 4.8814. Min Range: -4.8814

Max Act: 1.9661. Min Act: -0.0000

Data Index: 533238 (C4 (Web Text))

Max Activating Token Index: 976

Text #18

Max Range: 4.8814. Min Range: -4.8814

Max Act: 1.7967. Min Act: -0.0000

Data Index: 580565 (C4 (Web Text))

Max Activating Token Index: 423

Text #19

Max Range: 4.8814. Min Range: -4.8814

Max Act: 1.7284. Min Act: -0.0000

Data Index: 242181 (C4 (Web Text))

Max Activating Token Index: 540