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

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

Neuron 2515 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.7163. Min Act: -0.0001

Data Index: 757598 (C4 (Web Text))

Max Activating Token Index: 646

Text #1

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.6671. Min Act: -0.0001

Data Index: 176095 (C4 (Web Text))

Max Activating Token Index: 262

Text #2

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.6292. Min Act: -0.0001

Data Index: 321390 (C4 (Web Text))

Max Activating Token Index: 301

Text #3

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.5763. Min Act: -0.0001

Data Index: 1268832 (C4 (Web Text))

Max Activating Token Index: 669

Text #4

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.5759. Min Act: -0.0001

Data Index: 44055 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.5183. Min Act: -0.0001

Data Index: 44831 (C4 (Web Text))

Max Activating Token Index: 687

Text #6

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.5338. Min Act: -0.0001

Data Index: 582528 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.5098. Min Act: -0.0001

Data Index: 1256143 (C4 (Web Text))

Max Activating Token Index: 813

Text #8

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.4913. Min Act: -0.0001

Data Index: 711951 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.5039. Min Act: -0.0001

Data Index: 595323 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.4696. Min Act: -0.0001

Data Index: 1174955 (C4 (Web Text))

Max Activating Token Index: 215

Text #11

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.5194. Min Act: -0.0001

Data Index: 55765 (C4 (Web Text))

Max Activating Token Index: 355

Text #12

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.4990. Min Act: -0.0001

Data Index: 26074 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.5101. Min Act: -0.0001

Data Index: 1336491 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.4940. Min Act: -0.0001

Data Index: 309770 (C4 (Web Text))

Max Activating Token Index: 1005

Text #15

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.4586. Min Act: -0.0001

Data Index: 988137 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.4742. Min Act: -0.0001

Data Index: 1050612 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.4726. Min Act: -0.0001

Data Index: 528234 (C4 (Web Text))

Max Activating Token Index: 999

Text #18

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.5033. Min Act: -0.0001

Data Index: 347018 (C4 (Web Text))

Max Activating Token Index: 987

Text #19

Max Range: 0.7163. Min Range: -0.7163

Max Act: 0.4714. Min Act: -0.0001

Data Index: 375949 (C4 (Web Text))

Max Activating Token Index: 957