Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3474 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.2670. Min Range: -2.2670

Max Act: 2.1095. Min Act: -0.0001

Data Index: 94351 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 2.2670. Min Range: -2.2670

Max Act: 2.2670. Min Act: -0.0000

Data Index: 616682 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 2.2670. Min Range: -2.2670

Max Act: 1.9541. Min Act: -0.0000

Data Index: 1527228 (Python Code)

Max Activating Token Index: 85

Text #3

Max Range: 2.2670. Min Range: -2.2670

Max Act: 2.0007. Min Act: -0.0000

Data Index: 1126452 (C4 (Web Text))

Max Activating Token Index: 904

Text #4

Max Range: 2.2670. Min Range: -2.2670

Max Act: 1.9139. Min Act: -0.0000

Data Index: 1077476 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 2.2670. Min Range: -2.2670

Max Act: 2.0697. Min Act: -0.0000

Data Index: 818652 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 2.2670. Min Range: -2.2670

Max Act: 1.4842. Min Act: -0.0000

Data Index: 446880 (C4 (Web Text))

Max Activating Token Index: 812

Text #7

Max Range: 2.2670. Min Range: -2.2670

Max Act: 1.6834. Min Act: -0.0000

Data Index: 747221 (C4 (Web Text))

Max Activating Token Index: 326

Text #8

Max Range: 2.2670. Min Range: -2.2670

Max Act: 1.7605. Min Act: -0.0001

Data Index: 1403733 (Python Code)

Max Activating Token Index: 459

Text #9

Max Range: 2.2670. Min Range: -2.2670

Max Act: 1.6736. Min Act: -0.0001

Data Index: 1542247 (Python Code)

Max Activating Token Index: 162

Text #10

Max Range: 2.2670. Min Range: -2.2670

Max Act: 1.6446. Min Act: -0.0000

Data Index: 1475053 (Python Code)

Max Activating Token Index: 793

Text #11

Max Range: 2.2670. Min Range: -2.2670

Max Act: 1.7764. Min Act: -0.0000

Data Index: 1219186 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 2.2670. Min Range: -2.2670

Max Act: 1.5489. Min Act: -0.0000

Data Index: 852677 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 2.2670. Min Range: -2.2670

Max Act: 1.5056. Min Act: -0.0000

Data Index: 1290312 (C4 (Web Text))

Max Activating Token Index: 315

Text #14

Max Range: 2.2670. Min Range: -2.2670

Max Act: 1.6648. Min Act: -0.0000

Data Index: 321024 (C4 (Web Text))

Max Activating Token Index: 75

Text #15

Max Range: 2.2670. Min Range: -2.2670

Max Act: 1.5288. Min Act: -0.0000

Data Index: 767420 (C4 (Web Text))

Max Activating Token Index: 356

Text #16

Max Range: 2.2670. Min Range: -2.2670

Max Act: 1.4777. Min Act: -0.0000

Data Index: 703840 (C4 (Web Text))

Max Activating Token Index: 980

Text #17

Max Range: 2.2670. Min Range: -2.2670

Max Act: 1.5886. Min Act: -0.0001

Data Index: 1444754 (Python Code)

Max Activating Token Index: 263

Text #18

Max Range: 2.2670. Min Range: -2.2670

Max Act: 1.5312. Min Act: -0.0000

Data Index: 1529348 (Python Code)

Max Activating Token Index: 982

Text #19

Max Range: 2.2670. Min Range: -2.2670

Max Act: 1.7617. Min Act: -0.0000

Data Index: 1532415 (Python Code)

Max Activating Token Index: 634