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

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

Neuron 1522 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: 0.8240. Min Range: -0.8240

Max Act: 0.8240. Min Act: -0.0001

Data Index: 1028766 (C4 (Web Text))

Max Activating Token Index: 124

Text #1

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.8116. Min Act: -0.0001

Data Index: 1174894 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.7648. Min Act: -0.0001

Data Index: 127077 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.7489. Min Act: -0.0001

Data Index: 1241571 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.6940. Min Act: -0.0001

Data Index: 791378 (C4 (Web Text))

Max Activating Token Index: 959

Text #5

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.6872. Min Act: -0.0001

Data Index: 1186555 (C4 (Web Text))

Max Activating Token Index: 546

Text #6

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.6892. Min Act: -0.0001

Data Index: 163807 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.6811. Min Act: -0.0001

Data Index: 1357692 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.6707. Min Act: -0.0001

Data Index: 332908 (C4 (Web Text))

Max Activating Token Index: 827

Text #9

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.6555. Min Act: -0.0001

Data Index: 1052786 (C4 (Web Text))

Max Activating Token Index: 959

Text #10

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.6806. Min Act: -0.0001

Data Index: 550782 (C4 (Web Text))

Max Activating Token Index: 888

Text #11

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.6662. Min Act: -0.0000

Data Index: 1036178 (C4 (Web Text))

Max Activating Token Index: 263

Text #12

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.6535. Min Act: -0.0001

Data Index: 1004843 (C4 (Web Text))

Max Activating Token Index: 622

Text #13

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.6996. Min Act: -0.0001

Data Index: 939390 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.6519. Min Act: -0.0001

Data Index: 1587419 (Python Code)

Max Activating Token Index: 283

Text #15

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.6245. Min Act: -0.0001

Data Index: 360535 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.6462. Min Act: -0.0001

Data Index: 213834 (C4 (Web Text))

Max Activating Token Index: 870

Text #17

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.6249. Min Act: -0.0001

Data Index: 791875 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.6202. Min Act: -0.0001

Data Index: 498338 (C4 (Web Text))

Max Activating Token Index: 395

Text #19

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.5916. Min Act: -0.0001

Data Index: 802152 (C4 (Web Text))

Max Activating Token Index: 217