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

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

Neuron 1410 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.4946. Min Act: -0.0000

Data Index: 1268216 (C4 (Web Text))

Max Activating Token Index: 881

Text #1

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.4355. Min Act: -0.0000

Data Index: 1076664 (C4 (Web Text))

Max Activating Token Index: 983

Text #2

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.4206. Min Act: -0.0000

Data Index: 1150193 (C4 (Web Text))

Max Activating Token Index: 476

Text #3

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.4167. Min Act: -0.0000

Data Index: 433220 (C4 (Web Text))

Max Activating Token Index: 538

Text #4

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.4036. Min Act: -0.0000

Data Index: 2955 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.4049. Min Act: 0.0000

Data Index: 289496 (C4 (Web Text))

Max Activating Token Index: 374

Text #6

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3903. Min Act: -0.0000

Data Index: 634701 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3713. Min Act: -0.0000

Data Index: 638011 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3673. Min Act: -0.0000

Data Index: 768750 (C4 (Web Text))

Max Activating Token Index: 430

Text #9

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3657. Min Act: -0.0000

Data Index: 668255 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3695. Min Act: -0.0000

Data Index: 1142976 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3553. Min Act: -0.0000

Data Index: 505487 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3747. Min Act: 0.0000

Data Index: 964618 (C4 (Web Text))

Max Activating Token Index: 754

Text #13

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3578. Min Act: -0.0000

Data Index: 205228 (C4 (Web Text))

Max Activating Token Index: 630

Text #14

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3544. Min Act: -0.0000

Data Index: 670909 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3416. Min Act: -0.0000

Data Index: 554133 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3386. Min Act: -0.0000

Data Index: 1324520 (C4 (Web Text))

Max Activating Token Index: 943

Text #17

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3472. Min Act: -0.0000

Data Index: 193389 (C4 (Web Text))

Max Activating Token Index: 172

Text #18

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3262. Min Act: -0.0000

Data Index: 194896 (C4 (Web Text))

Max Activating Token Index: 447

Text #19

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3358. Min Act: -0.0000

Data Index: 838863 (C4 (Web Text))

Max Activating Token Index: 863