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

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

Neuron 3061 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0063. Min Act: -0.0001

Data Index: 355733 (C4 (Web Text))

Max Activating Token Index: 480

Text #1

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0059. Min Act: 0.0000

Data Index: 522574 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0053. Min Act: -0.0000

Data Index: 1291097 (C4 (Web Text))

Max Activating Token Index: 480

Text #3

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0052. Min Act: -0.0001

Data Index: 421550 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0054. Min Act: -0.0000

Data Index: 1034468 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0051. Min Act: -0.0000

Data Index: 115219 (C4 (Web Text))

Max Activating Token Index: 339

Text #6

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0052. Min Act: -0.0000

Data Index: 526202 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0052. Min Act: -0.0000

Data Index: 861632 (C4 (Web Text))

Max Activating Token Index: 539

Text #8

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0051. Min Act: -0.0000

Data Index: 1539460 (Python Code)

Max Activating Token Index: 478

Text #9

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0050. Min Act: -0.0000

Data Index: 331040 (C4 (Web Text))

Max Activating Token Index: 330

Text #10

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0052. Min Act: -0.0000

Data Index: 399651 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0052. Min Act: -0.0000

Data Index: 1463605 (Python Code)

Max Activating Token Index: 623

Text #12

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0050. Min Act: -0.0001

Data Index: 346991 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0050. Min Act: -0.0001

Data Index: 307278 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0051. Min Act: -0.0000

Data Index: 1218564 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0052. Min Act: -0.0001

Data Index: 1155618 (C4 (Web Text))

Max Activating Token Index: 282

Text #16

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0051. Min Act: 0.0000

Data Index: 1063080 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0051. Min Act: 0.0000

Data Index: 84166 (C4 (Web Text))

Max Activating Token Index: 277

Text #18

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0050. Min Act: -0.0001

Data Index: 441534 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 0.0063. Min Range: -0.0063

Max Act: 0.0050. Min Act: 0.0000

Data Index: 1428106 (Python Code)

Max Activating Token Index: 593