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

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

Neuron 3088 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5420. Min Range: -2.5420

Max Act: 2.5420. Min Act: -0.0000

Data Index: 1646661 (Python Code)

Max Activating Token Index: 111

Text #1

Max Range: 2.5420. Min Range: -2.5420

Max Act: 2.2480. Min Act: -0.0000

Data Index: 1538592 (Python Code)

Max Activating Token Index: 453

Text #2

Max Range: 2.5420. Min Range: -2.5420

Max Act: 2.1310. Min Act: -0.0000

Data Index: 1571410 (Python Code)

Max Activating Token Index: 252

Text #3

Max Range: 2.5420. Min Range: -2.5420

Max Act: 2.0144. Min Act: -0.0000

Data Index: 1566806 (Python Code)

Max Activating Token Index: 909

Text #4

Max Range: 2.5420. Min Range: -2.5420

Max Act: 2.0963. Min Act: -0.0000

Data Index: 1648758 (Python Code)

Max Activating Token Index: 65

Text #5

Max Range: 2.5420. Min Range: -2.5420

Max Act: 1.7812. Min Act: -0.0000

Data Index: 1477891 (Python Code)

Max Activating Token Index: 246

Text #6

Max Range: 2.5420. Min Range: -2.5420

Max Act: 1.9500. Min Act: -0.0000

Data Index: 1562714 (Python Code)

Max Activating Token Index: 367

Text #7

Max Range: 2.5420. Min Range: -2.5420

Max Act: 1.9070. Min Act: -0.0000

Data Index: 1510858 (Python Code)

Max Activating Token Index: 597

Text #8

Max Range: 2.5420. Min Range: -2.5420

Max Act: 1.7902. Min Act: -0.0000

Data Index: 1656154 (Python Code)

Max Activating Token Index: 601

Text #9

Max Range: 2.5420. Min Range: -2.5420

Max Act: 1.8525. Min Act: -0.0000

Data Index: 1578370 (Python Code)

Max Activating Token Index: 373

Text #10

Max Range: 2.5420. Min Range: -2.5420

Max Act: 1.7524. Min Act: -0.0000

Data Index: 1527430 (Python Code)

Max Activating Token Index: 151

Text #11

Max Range: 2.5420. Min Range: -2.5420

Max Act: 1.7161. Min Act: -0.0000

Data Index: 1397657 (Python Code)

Max Activating Token Index: 31

Text #12

Max Range: 2.5420. Min Range: -2.5420

Max Act: 1.7168. Min Act: -0.0000

Data Index: 1433909 (Python Code)

Max Activating Token Index: 516

Text #13

Max Range: 2.5420. Min Range: -2.5420

Max Act: 1.7998. Min Act: -0.0000

Data Index: 1558034 (Python Code)

Max Activating Token Index: 366

Text #14

Max Range: 2.5420. Min Range: -2.5420

Max Act: 1.6867. Min Act: -0.0000

Data Index: 1519505 (Python Code)

Max Activating Token Index: 631

Text #15

Max Range: 2.5420. Min Range: -2.5420

Max Act: 1.7440. Min Act: -0.0000

Data Index: 1398154 (Python Code)

Max Activating Token Index: 529

Text #16

Max Range: 2.5420. Min Range: -2.5420

Max Act: 1.4732. Min Act: -0.0000

Data Index: 1587146 (Python Code)

Max Activating Token Index: 265

Text #17

Max Range: 2.5420. Min Range: -2.5420

Max Act: 1.6540. Min Act: -0.0000

Data Index: 1486712 (Python Code)

Max Activating Token Index: 746

Text #18

Max Range: 2.5420. Min Range: -2.5420

Max Act: 1.6261. Min Act: -0.0000

Data Index: 1641737 (Python Code)

Max Activating Token Index: 164

Text #19

Max Range: 2.5420. Min Range: -2.5420

Max Act: 1.6934. Min Act: -0.0000

Data Index: 1460831 (Python Code)

Max Activating Token Index: 936