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

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

Neuron 2353 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: 2.7069. Min Range: -2.7069

Max Act: 2.7069. Min Act: -0.0000

Data Index: 806633 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 2.7069. Min Range: -2.7069

Max Act: 1.9680. Min Act: -0.0000

Data Index: 1055243 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 2.7069. Min Range: -2.7069

Max Act: 1.7104. Min Act: -0.0000

Data Index: 708192 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 2.7069. Min Range: -2.7069

Max Act: 1.5662. Min Act: -0.0000

Data Index: 917415 (C4 (Web Text))

Max Activating Token Index: 447

Text #4

Max Range: 2.7069. Min Range: -2.7069

Max Act: 1.6518. Min Act: -0.0000

Data Index: 625233 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 2.7069. Min Range: -2.7069

Max Act: 1.6671. Min Act: -0.0000

Data Index: 20185 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 2.7069. Min Range: -2.7069

Max Act: 1.5468. Min Act: -0.0000

Data Index: 1170921 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 2.7069. Min Range: -2.7069

Max Act: 1.5415. Min Act: -0.0000

Data Index: 393173 (C4 (Web Text))

Max Activating Token Index: 442

Text #8

Max Range: 2.7069. Min Range: -2.7069

Max Act: 1.4878. Min Act: -0.0000

Data Index: 320668 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 2.7069. Min Range: -2.7069

Max Act: 1.4948. Min Act: -0.0000

Data Index: 946293 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 2.7069. Min Range: -2.7069

Max Act: 1.4497. Min Act: -0.0000

Data Index: 804614 (C4 (Web Text))

Max Activating Token Index: 817

Text #11

Max Range: 2.7069. Min Range: -2.7069

Max Act: 1.4359. Min Act: -0.0000

Data Index: 897078 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 2.7069. Min Range: -2.7069

Max Act: 1.5088. Min Act: -0.0000

Data Index: 1079372 (C4 (Web Text))

Max Activating Token Index: 787

Text #13

Max Range: 2.7069. Min Range: -2.7069

Max Act: 1.3834. Min Act: -0.0000

Data Index: 1340281 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 2.7069. Min Range: -2.7069

Max Act: 1.4251. Min Act: -0.0000

Data Index: 1094959 (C4 (Web Text))

Max Activating Token Index: 348

Text #15

Max Range: 2.7069. Min Range: -2.7069

Max Act: 1.2874. Min Act: -0.0000

Data Index: 1206832 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 2.7069. Min Range: -2.7069

Max Act: 1.1214. Min Act: -0.0000

Data Index: 566471 (C4 (Web Text))

Max Activating Token Index: 379

Text #17

Max Range: 2.7069. Min Range: -2.7069

Max Act: 1.3153. Min Act: -0.0000

Data Index: 1200420 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 2.7069. Min Range: -2.7069

Max Act: 1.1544. Min Act: -0.0000

Data Index: 1036550 (C4 (Web Text))

Max Activating Token Index: 638

Text #19

Max Range: 2.7069. Min Range: -2.7069

Max Act: 1.1392. Min Act: -0.0000

Data Index: 819007 (C4 (Web Text))

Max Activating Token Index: 260