Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4758 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9876. Min Range: -0.9876

Max Act: 0.9876. Min Act: -0.0000

Data Index: 1225391 (C4 (Web Text))

Max Activating Token Index: 985

Text #1

Max Range: 0.9876. Min Range: -0.9876

Max Act: 0.9690. Min Act: -0.0000

Data Index: 369129 (C4 (Web Text))

Max Activating Token Index: 276

Text #2

Max Range: 0.9876. Min Range: -0.9876

Max Act: 0.9534. Min Act: -0.0000

Data Index: 18663 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 0.9876. Min Range: -0.9876

Max Act: 0.9166. Min Act: -0.0000

Data Index: 380771 (C4 (Web Text))

Max Activating Token Index: 856

Text #4

Max Range: 0.9876. Min Range: -0.9876

Max Act: 0.8813. Min Act: -0.0000

Data Index: 1070375 (C4 (Web Text))

Max Activating Token Index: 812

Text #5

Max Range: 0.9876. Min Range: -0.9876

Max Act: 0.8184. Min Act: -0.0000

Data Index: 335292 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 0.9876. Min Range: -0.9876

Max Act: 0.8442. Min Act: -0.0000

Data Index: 1163151 (C4 (Web Text))

Max Activating Token Index: 238

Text #7

Max Range: 0.9876. Min Range: -0.9876

Max Act: 0.8184. Min Act: -0.0000

Data Index: 940086 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 0.9876. Min Range: -0.9876

Max Act: 0.8377. Min Act: 0.0000

Data Index: 277764 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 0.9876. Min Range: -0.9876

Max Act: 0.8293. Min Act: -0.0000

Data Index: 1129743 (C4 (Web Text))

Max Activating Token Index: 471

Text #10

Max Range: 0.9876. Min Range: -0.9876

Max Act: 0.8477. Min Act: -0.0000

Data Index: 240089 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 0.9876. Min Range: -0.9876

Max Act: 0.8177. Min Act: -0.0000

Data Index: 600044 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 0.9876. Min Range: -0.9876

Max Act: 0.8188. Min Act: -0.0000

Data Index: 1122075 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 0.9876. Min Range: -0.9876

Max Act: 0.8151. Min Act: -0.0000

Data Index: 1372629 (Python Code)

Max Activating Token Index: 489

Text #14

Max Range: 0.9876. Min Range: -0.9876

Max Act: 0.8629. Min Act: -0.0000

Data Index: 542379 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 0.9876. Min Range: -0.9876

Max Act: 0.7849. Min Act: -0.0000

Data Index: 796959 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 0.9876. Min Range: -0.9876

Max Act: 0.7769. Min Act: -0.0000

Data Index: 669335 (C4 (Web Text))

Max Activating Token Index: 313

Text #17

Max Range: 0.9876. Min Range: -0.9876

Max Act: 0.7938. Min Act: -0.0000

Data Index: 505837 (C4 (Web Text))

Max Activating Token Index: 406

Text #18

Max Range: 0.9876. Min Range: -0.9876

Max Act: 0.7875. Min Act: -0.0000

Data Index: 255159 (C4 (Web Text))

Max Activating Token Index: 667

Text #19

Max Range: 0.9876. Min Range: -0.9876

Max Act: 0.7657. Min Act: -0.0000

Data Index: 1052700 (C4 (Web Text))

Max Activating Token Index: 898