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

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

Neuron 3985 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0657. Min Range: -1.0657

Max Act: 1.0657. Min Act: -0.0000

Data Index: 1270280 (C4 (Web Text))

Max Activating Token Index: 497

Text #1

Max Range: 1.0657. Min Range: -1.0657

Max Act: 1.0398. Min Act: -0.0000

Data Index: 379544 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 1.0657. Min Range: -1.0657

Max Act: 1.0462. Min Act: -0.0000

Data Index: 674034 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 1.0657. Min Range: -1.0657

Max Act: 1.0313. Min Act: -0.0000

Data Index: 66997 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 1.0657. Min Range: -1.0657

Max Act: 1.0032. Min Act: -0.0000

Data Index: 307143 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 1.0657. Min Range: -1.0657

Max Act: 0.9850. Min Act: -0.0000

Data Index: 75602 (C4 (Web Text))

Max Activating Token Index: 536

Text #6

Max Range: 1.0657. Min Range: -1.0657

Max Act: 0.9968. Min Act: -0.0000

Data Index: 760599 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 1.0657. Min Range: -1.0657

Max Act: 0.9424. Min Act: -0.0000

Data Index: 1348230 (C4 (Web Text))

Max Activating Token Index: 135

Text #8

Max Range: 1.0657. Min Range: -1.0657

Max Act: 0.9798. Min Act: -0.0000

Data Index: 141594 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 1.0657. Min Range: -1.0657

Max Act: 0.9308. Min Act: -0.0000

Data Index: 1147354 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 1.0657. Min Range: -1.0657

Max Act: 0.9122. Min Act: -0.0000

Data Index: 69551 (C4 (Web Text))

Max Activating Token Index: 324

Text #11

Max Range: 1.0657. Min Range: -1.0657

Max Act: 0.9950. Min Act: -0.0000

Data Index: 217029 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 1.0657. Min Range: -1.0657

Max Act: 0.9115. Min Act: -0.0000

Data Index: 558200 (C4 (Web Text))

Max Activating Token Index: 739

Text #13

Max Range: 1.0657. Min Range: -1.0657

Max Act: 0.9099. Min Act: -0.0000

Data Index: 487816 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 1.0657. Min Range: -1.0657

Max Act: 0.8958. Min Act: -0.0000

Data Index: 1234867 (C4 (Web Text))

Max Activating Token Index: 253

Text #15

Max Range: 1.0657. Min Range: -1.0657

Max Act: 0.9234. Min Act: -0.0000

Data Index: 1063370 (C4 (Web Text))

Max Activating Token Index: 587

Text #16

Max Range: 1.0657. Min Range: -1.0657

Max Act: 0.9600. Min Act: -0.0000

Data Index: 116455 (C4 (Web Text))

Max Activating Token Index: 313

Text #17

Max Range: 1.0657. Min Range: -1.0657

Max Act: 0.9209. Min Act: -0.0000

Data Index: 652026 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 1.0657. Min Range: -1.0657

Max Act: 0.9168. Min Act: -0.0000

Data Index: 384747 (C4 (Web Text))

Max Activating Token Index: 633

Text #19

Max Range: 1.0657. Min Range: -1.0657

Max Act: 0.8740. Min Act: -0.0000

Data Index: 427381 (C4 (Web Text))

Max Activating Token Index: 223