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

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

Neuron 163 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2348. Min Range: -1.2348

Max Act: 1.2348. Min Act: -0.0001

Data Index: 130275 (C4 (Web Text))

Max Activating Token Index: 969

Text #1

Max Range: 1.2348. Min Range: -1.2348

Max Act: 1.0263. Min Act: -0.0001

Data Index: 456600 (C4 (Web Text))

Max Activating Token Index: 996

Text #2

Max Range: 1.2348. Min Range: -1.2348

Max Act: 1.0857. Min Act: -0.0001

Data Index: 940475 (C4 (Web Text))

Max Activating Token Index: 197

Text #3

Max Range: 1.2348. Min Range: -1.2348

Max Act: 1.0447. Min Act: -0.0001

Data Index: 129549 (C4 (Web Text))

Max Activating Token Index: 167

Text #4

Max Range: 1.2348. Min Range: -1.2348

Max Act: 1.0733. Min Act: -0.0001

Data Index: 17456 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 1.2348. Min Range: -1.2348

Max Act: 1.0037. Min Act: -0.0001

Data Index: 2931 (C4 (Web Text))

Max Activating Token Index: 368

Text #6

Max Range: 1.2348. Min Range: -1.2348

Max Act: 0.9238. Min Act: -0.0001

Data Index: 1212633 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 1.2348. Min Range: -1.2348

Max Act: 1.0104. Min Act: -0.0001

Data Index: 1271313 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 1.2348. Min Range: -1.2348

Max Act: 1.0409. Min Act: -0.0001

Data Index: 524546 (C4 (Web Text))

Max Activating Token Index: 840

Text #9

Max Range: 1.2348. Min Range: -1.2348

Max Act: 0.9652. Min Act: -0.0001

Data Index: 501891 (C4 (Web Text))

Max Activating Token Index: 138

Text #10

Max Range: 1.2348. Min Range: -1.2348

Max Act: 0.9973. Min Act: -0.0001

Data Index: 289415 (C4 (Web Text))

Max Activating Token Index: 209

Text #11

Max Range: 1.2348. Min Range: -1.2348

Max Act: 1.0088. Min Act: -0.0001

Data Index: 1147028 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 1.2348. Min Range: -1.2348

Max Act: 1.0160. Min Act: -0.0001

Data Index: 803929 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 1.2348. Min Range: -1.2348

Max Act: 0.8917. Min Act: -0.0001

Data Index: 628939 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 1.2348. Min Range: -1.2348

Max Act: 0.8630. Min Act: -0.0001

Data Index: 1172888 (C4 (Web Text))

Max Activating Token Index: 677

Text #15

Max Range: 1.2348. Min Range: -1.2348

Max Act: 0.9460. Min Act: -0.0001

Data Index: 1154859 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 1.2348. Min Range: -1.2348

Max Act: 0.9447. Min Act: -0.0001

Data Index: 913958 (C4 (Web Text))

Max Activating Token Index: 614

Text #17

Max Range: 1.2348. Min Range: -1.2348

Max Act: 0.9724. Min Act: -0.0001

Data Index: 304973 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 1.2348. Min Range: -1.2348

Max Act: 0.9033. Min Act: -0.0001

Data Index: 997325 (C4 (Web Text))

Max Activating Token Index: 236

Text #19

Max Range: 1.2348. Min Range: -1.2348

Max Act: 0.8482. Min Act: -0.0001

Data Index: 1239602 (C4 (Web Text))

Max Activating Token Index: 215