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

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

Neuron 370 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6502. Min Range: -0.6502

Max Act: 0.6452. Min Act: -0.0001

Data Index: 670767 (C4 (Web Text))

Max Activating Token Index: 1018

Text #1

Max Range: 0.6502. Min Range: -0.6502

Max Act: 0.6202. Min Act: -0.0001

Data Index: 1221598 (C4 (Web Text))

Max Activating Token Index: 322

Text #2

Max Range: 0.6502. Min Range: -0.6502

Max Act: 0.6502. Min Act: -0.0000

Data Index: 776106 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 0.6502. Min Range: -0.6502

Max Act: 0.6247. Min Act: -0.0000

Data Index: 1160500 (C4 (Web Text))

Max Activating Token Index: 1015

Text #4

Max Range: 0.6502. Min Range: -0.6502

Max Act: 0.5998. Min Act: -0.0000

Data Index: 1005254 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 0.6502. Min Range: -0.6502

Max Act: 0.5956. Min Act: -0.0001

Data Index: 1320807 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 0.6502. Min Range: -0.6502

Max Act: 0.5867. Min Act: -0.0000

Data Index: 529179 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 0.6502. Min Range: -0.6502

Max Act: 0.5553. Min Act: -0.0001

Data Index: 1015219 (C4 (Web Text))

Max Activating Token Index: 502

Text #8

Max Range: 0.6502. Min Range: -0.6502

Max Act: 0.5697. Min Act: -0.0000

Data Index: 26445 (C4 (Web Text))

Max Activating Token Index: 486

Text #9

Max Range: 0.6502. Min Range: -0.6502

Max Act: 0.5711. Min Act: -0.0001

Data Index: 871167 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 0.6502. Min Range: -0.6502

Max Act: 0.5848. Min Act: -0.0001

Data Index: 1017233 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 0.6502. Min Range: -0.6502

Max Act: 0.5483. Min Act: -0.0001

Data Index: 972587 (C4 (Web Text))

Max Activating Token Index: 270

Text #12

Max Range: 0.6502. Min Range: -0.6502

Max Act: 0.5841. Min Act: -0.0000

Data Index: 407311 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 0.6502. Min Range: -0.6502

Max Act: 0.5650. Min Act: -0.0001

Data Index: 1221801 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 0.6502. Min Range: -0.6502

Max Act: 0.5634. Min Act: -0.0001

Data Index: 115551 (C4 (Web Text))

Max Activating Token Index: 516

Text #15

Max Range: 0.6502. Min Range: -0.6502

Max Act: 0.5371. Min Act: -0.0001

Data Index: 507408 (C4 (Web Text))

Max Activating Token Index: 166

Text #16

Max Range: 0.6502. Min Range: -0.6502

Max Act: 0.5593. Min Act: -0.0000

Data Index: 78199 (C4 (Web Text))

Max Activating Token Index: 721

Text #17

Max Range: 0.6502. Min Range: -0.6502

Max Act: 0.5771. Min Act: -0.0000

Data Index: 70759 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 0.6502. Min Range: -0.6502

Max Act: 0.4579. Min Act: -0.0001

Data Index: 1233205 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 0.6502. Min Range: -0.6502

Max Act: 0.5057. Min Act: -0.0001

Data Index: 1281373 (C4 (Web Text))

Max Activating Token Index: 775