Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3887 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.5435. Min Act: -0.0000

Data Index: 1228925 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.5362. Min Act: -0.0000

Data Index: 1149495 (C4 (Web Text))

Max Activating Token Index: 999

Text #2

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.4842. Min Act: -0.0000

Data Index: 78061 (C4 (Web Text))

Max Activating Token Index: 946

Text #3

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.4754. Min Act: -0.0000

Data Index: 745660 (C4 (Web Text))

Max Activating Token Index: 942

Text #4

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.4334. Min Act: -0.0000

Data Index: 233685 (C4 (Web Text))

Max Activating Token Index: 667

Text #5

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.4658. Min Act: -0.0000

Data Index: 1301992 (C4 (Web Text))

Max Activating Token Index: 340

Text #6

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.4637. Min Act: -0.0000

Data Index: 162667 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.4580. Min Act: -0.0000

Data Index: 610075 (C4 (Web Text))

Max Activating Token Index: 446

Text #8

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.4566. Min Act: -0.0000

Data Index: 780835 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.4126. Min Act: -0.0000

Data Index: 861112 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.4504. Min Act: -0.0000

Data Index: 168180 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.4160. Min Act: -0.0000

Data Index: 420228 (C4 (Web Text))

Max Activating Token Index: 507

Text #12

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.4060. Min Act: -0.0000

Data Index: 1034023 (C4 (Web Text))

Max Activating Token Index: 985

Text #13

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.4170. Min Act: -0.0000

Data Index: 1156727 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.3864. Min Act: -0.0000

Data Index: 1136415 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.4146. Min Act: -0.0000

Data Index: 156633 (C4 (Web Text))

Max Activating Token Index: 547

Text #16

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.3993. Min Act: -0.0000

Data Index: 486128 (C4 (Web Text))

Max Activating Token Index: 430

Text #17

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.4281. Min Act: -0.0000

Data Index: 802823 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.3843. Min Act: -0.0000

Data Index: 629368 (C4 (Web Text))

Max Activating Token Index: 532

Text #19

Max Range: 0.5435. Min Range: -0.5435

Max Act: 0.4537. Min Act: -0.0000

Data Index: 351050 (C4 (Web Text))

Max Activating Token Index: 433