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

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

Neuron 4321 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.3912. Min Act: -0.0002

Data Index: 603367 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.3131. Min Act: -0.0002

Data Index: 1230999 (C4 (Web Text))

Max Activating Token Index: 473

Text #2

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.2820. Min Act: -0.0002

Data Index: 909766 (C4 (Web Text))

Max Activating Token Index: 431

Text #3

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.3040. Min Act: -0.0002

Data Index: 596965 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.2743. Min Act: -0.0002

Data Index: 1171978 (C4 (Web Text))

Max Activating Token Index: 448

Text #5

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.2514. Min Act: -0.0002

Data Index: 515064 (C4 (Web Text))

Max Activating Token Index: 882

Text #6

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.2533. Min Act: -0.0002

Data Index: 348569 (C4 (Web Text))

Max Activating Token Index: 246

Text #7

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.2199. Min Act: -0.0002

Data Index: 904237 (C4 (Web Text))

Max Activating Token Index: 273

Text #8

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.2361. Min Act: -0.0003

Data Index: 1008570 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.1962. Min Act: -0.0002

Data Index: 1333317 (C4 (Web Text))

Max Activating Token Index: 343

Text #10

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.1904. Min Act: -0.0002

Data Index: 551139 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.1606. Min Act: -0.0002

Data Index: 869240 (C4 (Web Text))

Max Activating Token Index: 685

Text #12

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.1472. Min Act: -0.0003

Data Index: 623662 (C4 (Web Text))

Max Activating Token Index: 270

Text #13

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.1678. Min Act: -0.0002

Data Index: 783973 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.1618. Min Act: -0.0003

Data Index: 926535 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.1484. Min Act: -0.0002

Data Index: 795786 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.1476. Min Act: -0.0002

Data Index: 1012556 (C4 (Web Text))

Max Activating Token Index: 299

Text #17

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.1249. Min Act: -0.0003

Data Index: 653019 (C4 (Web Text))

Max Activating Token Index: 935

Text #18

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.1238. Min Act: -0.0002

Data Index: 248966 (C4 (Web Text))

Max Activating Token Index: 712

Text #19

Max Range: 1.3912. Min Range: -1.3912

Max Act: 1.1175. Min Act: -0.0002

Data Index: 1058063 (C4 (Web Text))

Max Activating Token Index: 243