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

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

Neuron 4103 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4842. Min Range: -1.4842

Max Act: 1.4842. Min Act: -0.0000

Data Index: 772940 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 1.4842. Min Range: -1.4842

Max Act: 1.3835. Min Act: -0.0000

Data Index: 321215 (C4 (Web Text))

Max Activating Token Index: 777

Text #2

Max Range: 1.4842. Min Range: -1.4842

Max Act: 1.2710. Min Act: -0.0000

Data Index: 574882 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 1.4842. Min Range: -1.4842

Max Act: 1.3431. Min Act: -0.0000

Data Index: 325628 (C4 (Web Text))

Max Activating Token Index: 370

Text #4

Max Range: 1.4842. Min Range: -1.4842

Max Act: 1.2990. Min Act: -0.0000

Data Index: 668563 (C4 (Web Text))

Max Activating Token Index: 495

Text #5

Max Range: 1.4842. Min Range: -1.4842

Max Act: 1.0795. Min Act: -0.0000

Data Index: 383254 (C4 (Web Text))

Max Activating Token Index: 642

Text #6

Max Range: 1.4842. Min Range: -1.4842

Max Act: 1.2062. Min Act: -0.0000

Data Index: 786120 (C4 (Web Text))

Max Activating Token Index: 893

Text #7

Max Range: 1.4842. Min Range: -1.4842

Max Act: 1.0344. Min Act: -0.0000

Data Index: 1352248 (C4 (Web Text))

Max Activating Token Index: 266

Text #8

Max Range: 1.4842. Min Range: -1.4842

Max Act: 1.2165. Min Act: -0.0000

Data Index: 820198 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 1.4842. Min Range: -1.4842

Max Act: 1.1944. Min Act: -0.0000

Data Index: 861964 (C4 (Web Text))

Max Activating Token Index: 942

Text #10

Max Range: 1.4842. Min Range: -1.4842

Max Act: 1.2259. Min Act: -0.0000

Data Index: 391422 (C4 (Web Text))

Max Activating Token Index: 447

Text #11

Max Range: 1.4842. Min Range: -1.4842

Max Act: 1.2307. Min Act: -0.0000

Data Index: 695896 (C4 (Web Text))

Max Activating Token Index: 734

Text #12

Max Range: 1.4842. Min Range: -1.4842

Max Act: 1.2471. Min Act: -0.0000

Data Index: 500444 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 1.4842. Min Range: -1.4842

Max Act: 1.2148. Min Act: -0.0000

Data Index: 391330 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 1.4842. Min Range: -1.4842

Max Act: 1.2226. Min Act: -0.0000

Data Index: 447496 (C4 (Web Text))

Max Activating Token Index: 260

Text #15

Max Range: 1.4842. Min Range: -1.4842

Max Act: 1.2588. Min Act: -0.0000

Data Index: 1297510 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 1.4842. Min Range: -1.4842

Max Act: 1.1472. Min Act: -0.0000

Data Index: 361082 (C4 (Web Text))

Max Activating Token Index: 500

Text #17

Max Range: 1.4842. Min Range: -1.4842

Max Act: 1.1976. Min Act: -0.0000

Data Index: 215015 (C4 (Web Text))

Max Activating Token Index: 272

Text #18

Max Range: 1.4842. Min Range: -1.4842

Max Act: 1.1603. Min Act: -0.0000

Data Index: 847501 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 1.4842. Min Range: -1.4842

Max Act: 1.1906. Min Act: -0.0000

Data Index: 694390 (C4 (Web Text))

Max Activating Token Index: 297