Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 506 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.0124. Min Range: -1.0124

Max Act: 1.0124. Min Act: -0.0001

Data Index: 379697 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 1.0124. Min Range: -1.0124

Max Act: 0.9424. Min Act: -0.0001

Data Index: 826818 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 1.0124. Min Range: -1.0124

Max Act: 0.8751. Min Act: -0.0001

Data Index: 478329 (C4 (Web Text))

Max Activating Token Index: 480

Text #3

Max Range: 1.0124. Min Range: -1.0124

Max Act: 0.8413. Min Act: -0.0001

Data Index: 978623 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 1.0124. Min Range: -1.0124

Max Act: 0.9964. Min Act: -0.0001

Data Index: 942516 (C4 (Web Text))

Max Activating Token Index: 869

Text #5

Max Range: 1.0124. Min Range: -1.0124

Max Act: 0.8699. Min Act: -0.0001

Data Index: 554350 (C4 (Web Text))

Max Activating Token Index: 184

Text #6

Max Range: 1.0124. Min Range: -1.0124

Max Act: 0.8899. Min Act: -0.0001

Data Index: 1285663 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 1.0124. Min Range: -1.0124

Max Act: 0.8891. Min Act: -0.0001

Data Index: 434868 (C4 (Web Text))

Max Activating Token Index: 310

Text #8

Max Range: 1.0124. Min Range: -1.0124

Max Act: 0.8113. Min Act: -0.0001

Data Index: 1294317 (C4 (Web Text))

Max Activating Token Index: 914

Text #9

Max Range: 1.0124. Min Range: -1.0124

Max Act: 0.8628. Min Act: -0.0001

Data Index: 556130 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 1.0124. Min Range: -1.0124

Max Act: 0.8371. Min Act: -0.0001

Data Index: 397152 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 1.0124. Min Range: -1.0124

Max Act: 0.8640. Min Act: -0.0001

Data Index: 1232551 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 1.0124. Min Range: -1.0124

Max Act: 0.8602. Min Act: -0.0001

Data Index: 991149 (C4 (Web Text))

Max Activating Token Index: 276

Text #13

Max Range: 1.0124. Min Range: -1.0124

Max Act: 0.8087. Min Act: -0.0001

Data Index: 307591 (C4 (Web Text))

Max Activating Token Index: 977

Text #14

Max Range: 1.0124. Min Range: -1.0124

Max Act: 0.8273. Min Act: -0.0001

Data Index: 232712 (C4 (Web Text))

Max Activating Token Index: 914

Text #15

Max Range: 1.0124. Min Range: -1.0124

Max Act: 0.7784. Min Act: -0.0001

Data Index: 906900 (C4 (Web Text))

Max Activating Token Index: 1005

Text #16

Max Range: 1.0124. Min Range: -1.0124

Max Act: 0.8058. Min Act: -0.0001

Data Index: 975870 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 1.0124. Min Range: -1.0124

Max Act: 0.9064. Min Act: -0.0001

Data Index: 1211902 (C4 (Web Text))

Max Activating Token Index: 691

Text #18

Max Range: 1.0124. Min Range: -1.0124

Max Act: 0.8168. Min Act: -0.0001

Data Index: 1305699 (C4 (Web Text))

Max Activating Token Index: 497

Text #19

Max Range: 1.0124. Min Range: -1.0124

Max Act: 0.8365. Min Act: -0.0001

Data Index: 299419 (C4 (Web Text))

Max Activating Token Index: 23