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

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

Neuron 3341 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6117. Min Range: -0.6117

Max Act: 0.6117. Min Act: -0.0000

Data Index: 903728 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 0.6117. Min Range: -0.6117

Max Act: 0.5154. Min Act: -0.0000

Data Index: 14355 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 0.6117. Min Range: -0.6117

Max Act: 0.4872. Min Act: -0.0001

Data Index: 1653541 (Python Code)

Max Activating Token Index: 104

Text #3

Max Range: 0.6117. Min Range: -0.6117

Max Act: 0.4827. Min Act: -0.0001

Data Index: 1648041 (Python Code)

Max Activating Token Index: 809

Text #4

Max Range: 0.6117. Min Range: -0.6117

Max Act: 0.4945. Min Act: -0.0001

Data Index: 1376679 (Python Code)

Max Activating Token Index: 810

Text #5

Max Range: 0.6117. Min Range: -0.6117

Max Act: 0.4440. Min Act: -0.0001

Data Index: 1366169 (Python Code)

Max Activating Token Index: 707

Text #6

Max Range: 0.6117. Min Range: -0.6117

Max Act: 0.4283. Min Act: -0.0000

Data Index: 587944 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 0.6117. Min Range: -0.6117

Max Act: 0.4135. Min Act: -0.0000

Data Index: 214227 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 0.6117. Min Range: -0.6117

Max Act: 0.4258. Min Act: -0.0001

Data Index: 926393 (C4 (Web Text))

Max Activating Token Index: 441

Text #9

Max Range: 0.6117. Min Range: -0.6117

Max Act: 0.4336. Min Act: -0.0001

Data Index: 1461717 (Python Code)

Max Activating Token Index: 209

Text #10

Max Range: 0.6117. Min Range: -0.6117

Max Act: 0.4167. Min Act: -0.0000

Data Index: 483038 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 0.6117. Min Range: -0.6117

Max Act: 0.4088. Min Act: -0.0001

Data Index: 564047 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 0.6117. Min Range: -0.6117

Max Act: 0.4191. Min Act: -0.0000

Data Index: 1581145 (Python Code)

Max Activating Token Index: 698

Text #13

Max Range: 0.6117. Min Range: -0.6117

Max Act: 0.4153. Min Act: -0.0001

Data Index: 1369343 (Python Code)

Max Activating Token Index: 262

Text #14

Max Range: 0.6117. Min Range: -0.6117

Max Act: 0.4106. Min Act: -0.0001

Data Index: 1387959 (Python Code)

Max Activating Token Index: 1003

Text #15

Max Range: 0.6117. Min Range: -0.6117

Max Act: 0.4094. Min Act: -0.0001

Data Index: 412906 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 0.6117. Min Range: -0.6117

Max Act: 0.3769. Min Act: -0.0000

Data Index: 1594521 (Python Code)

Max Activating Token Index: 386

Text #17

Max Range: 0.6117. Min Range: -0.6117

Max Act: 0.3903. Min Act: -0.0000

Data Index: 594058 (C4 (Web Text))

Max Activating Token Index: 892

Text #18

Max Range: 0.6117. Min Range: -0.6117

Max Act: 0.3784. Min Act: -0.0001

Data Index: 1403243 (Python Code)

Max Activating Token Index: 838

Text #19

Max Range: 0.6117. Min Range: -0.6117

Max Act: 0.3882. Min Act: -0.0000

Data Index: 67732 (C4 (Web Text))

Max Activating Token Index: 429