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

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

Neuron 928 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.7743. Min Act: -0.0001

Data Index: 53499 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.7749. Min Act: -0.0001

Data Index: 508965 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.6750. Min Act: -0.0001

Data Index: 742260 (C4 (Web Text))

Max Activating Token Index: 165

Text #3

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.6667. Min Act: -0.0001

Data Index: 472977 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.6467. Min Act: -0.0001

Data Index: 440099 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.6435. Min Act: -0.0001

Data Index: 235940 (C4 (Web Text))

Max Activating Token Index: 608

Text #6

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.5991. Min Act: -0.0001

Data Index: 170474 (C4 (Web Text))

Max Activating Token Index: 579

Text #7

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.6592. Min Act: -0.0001

Data Index: 1215346 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.5961. Min Act: -0.0001

Data Index: 476171 (C4 (Web Text))

Max Activating Token Index: 359

Text #9

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.6126. Min Act: -0.0000

Data Index: 1009382 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.5649. Min Act: -0.0001

Data Index: 1523011 (Python Code)

Max Activating Token Index: 465

Text #11

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.5697. Min Act: -0.0001

Data Index: 699298 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.5719. Min Act: -0.0000

Data Index: 1244929 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.5496. Min Act: -0.0001

Data Index: 415593 (C4 (Web Text))

Max Activating Token Index: 379

Text #14

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.5424. Min Act: -0.0000

Data Index: 1228183 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.5259. Min Act: -0.0000

Data Index: 86951 (C4 (Web Text))

Max Activating Token Index: 263

Text #16

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.5243. Min Act: -0.0001

Data Index: 1249168 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.5549. Min Act: -0.0001

Data Index: 1301377 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.5556. Min Act: -0.0001

Data Index: 278380 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.5224. Min Act: -0.0001

Data Index: 711836 (C4 (Web Text))

Max Activating Token Index: 176