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

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

Neuron 3364 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: 0.7094. Min Range: -0.7094

Max Act: 0.7094. Min Act: -0.0002

Data Index: 1157755 (C4 (Web Text))

Max Activating Token Index: 601

Text #1

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.6938. Min Act: -0.0001

Data Index: 507626 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.6775. Min Act: -0.0001

Data Index: 1197291 (C4 (Web Text))

Max Activating Token Index: 274

Text #3

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.6221. Min Act: -0.0001

Data Index: 980191 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.6246. Min Act: -0.0001

Data Index: 600209 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.6021. Min Act: -0.0002

Data Index: 61246 (C4 (Web Text))

Max Activating Token Index: 520

Text #6

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.6075. Min Act: -0.0002

Data Index: 1191536 (C4 (Web Text))

Max Activating Token Index: 983

Text #7

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.6048. Min Act: -0.0001

Data Index: 1213445 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.6243. Min Act: -0.0002

Data Index: 337433 (C4 (Web Text))

Max Activating Token Index: 244

Text #9

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.6197. Min Act: -0.0001

Data Index: 690751 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.6119. Min Act: -0.0002

Data Index: 595363 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.5686. Min Act: -0.0001

Data Index: 622173 (C4 (Web Text))

Max Activating Token Index: 723

Text #12

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.5805. Min Act: -0.0002

Data Index: 1091845 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.5933. Min Act: -0.0001

Data Index: 1052962 (C4 (Web Text))

Max Activating Token Index: 95

Text #14

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.5932. Min Act: -0.0002

Data Index: 460152 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.6083. Min Act: -0.0001

Data Index: 70984 (C4 (Web Text))

Max Activating Token Index: 587

Text #16

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.6070. Min Act: -0.0002

Data Index: 880301 (C4 (Web Text))

Max Activating Token Index: 164

Text #17

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.5830. Min Act: -0.0001

Data Index: 603854 (C4 (Web Text))

Max Activating Token Index: 412

Text #18

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.5832. Min Act: -0.0001

Data Index: 132854 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 0.7094. Min Range: -0.7094

Max Act: 0.6230. Min Act: -0.0002

Data Index: 946154 (C4 (Web Text))

Max Activating Token Index: 980