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

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

Neuron 1653 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.5837. Min Act: -0.0000

Data Index: 925248 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.5345. Min Act: -0.0000

Data Index: 999412 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4901. Min Act: -0.0000

Data Index: 44419 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4720. Min Act: -0.0000

Data Index: 1202056 (C4 (Web Text))

Max Activating Token Index: 597

Text #4

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4420. Min Act: -0.0000

Data Index: 918536 (C4 (Web Text))

Max Activating Token Index: 667

Text #5

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4713. Min Act: -0.0000

Data Index: 1238314 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4092. Min Act: -0.0000

Data Index: 1023234 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.3824. Min Act: -0.0000

Data Index: 551240 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.4184. Min Act: -0.0000

Data Index: 909301 (C4 (Web Text))

Max Activating Token Index: 490

Text #9

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.3705. Min Act: -0.0000

Data Index: 895677 (C4 (Web Text))

Max Activating Token Index: 763

Text #10

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.3632. Min Act: -0.0000

Data Index: 859753 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.3510. Min Act: 0.0001

Data Index: 802655 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.3512. Min Act: -0.0000

Data Index: 489403 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.3627. Min Act: 0.0003

Data Index: 324927 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.3477. Min Act: -0.0000

Data Index: 742199 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.3594. Min Act: -0.0000

Data Index: 1055838 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.3559. Min Act: -0.0000

Data Index: 174227 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.3333. Min Act: 0.0001

Data Index: 696321 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.3423. Min Act: 0.0000

Data Index: 201043 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 0.5837. Min Range: -0.5837

Max Act: 0.3289. Min Act: -0.0000

Data Index: 1341535 (C4 (Web Text))

Max Activating Token Index: 339