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

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

Neuron 1898 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6003. Min Range: -2.6003

Max Act: 2.6003. Min Act: -0.0000

Data Index: 267446 (C4 (Web Text))

Max Activating Token Index: 562

Text #1

Max Range: 2.6003. Min Range: -2.6003

Max Act: 2.4633. Min Act: -0.0000

Data Index: 938561 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 2.6003. Min Range: -2.6003

Max Act: 2.4190. Min Act: -0.0000

Data Index: 497282 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 2.6003. Min Range: -2.6003

Max Act: 2.2863. Min Act: -0.0000

Data Index: 76439 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 2.6003. Min Range: -2.6003

Max Act: 2.2947. Min Act: -0.0000

Data Index: 1253214 (C4 (Web Text))

Max Activating Token Index: 609

Text #5

Max Range: 2.6003. Min Range: -2.6003

Max Act: 2.3978. Min Act: -0.0000

Data Index: 1284854 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 2.6003. Min Range: -2.6003

Max Act: 2.2612. Min Act: -0.0000

Data Index: 1166509 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 2.6003. Min Range: -2.6003

Max Act: 2.3602. Min Act: -0.0000

Data Index: 509551 (C4 (Web Text))

Max Activating Token Index: 871

Text #8

Max Range: 2.6003. Min Range: -2.6003

Max Act: 2.4433. Min Act: -0.0000

Data Index: 949215 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 2.6003. Min Range: -2.6003

Max Act: 2.3084. Min Act: -0.0000

Data Index: 757600 (C4 (Web Text))

Max Activating Token Index: 244

Text #10

Max Range: 2.6003. Min Range: -2.6003

Max Act: 2.0778. Min Act: -0.0000

Data Index: 953121 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 2.6003. Min Range: -2.6003

Max Act: 2.1785. Min Act: -0.0000

Data Index: 438219 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 2.6003. Min Range: -2.6003

Max Act: 2.2715. Min Act: -0.0000

Data Index: 973958 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 2.6003. Min Range: -2.6003

Max Act: 2.0531. Min Act: -0.0000

Data Index: 630530 (C4 (Web Text))

Max Activating Token Index: 213

Text #14

Max Range: 2.6003. Min Range: -2.6003

Max Act: 2.0383. Min Act: -0.0000

Data Index: 810196 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 2.6003. Min Range: -2.6003

Max Act: 2.2541. Min Act: -0.0000

Data Index: 298446 (C4 (Web Text))

Max Activating Token Index: 154

Text #16

Max Range: 2.6003. Min Range: -2.6003

Max Act: 1.9935. Min Act: -0.0000

Data Index: 1130813 (C4 (Web Text))

Max Activating Token Index: 240

Text #17

Max Range: 2.6003. Min Range: -2.6003

Max Act: 2.2454. Min Act: -0.0000

Data Index: 308139 (C4 (Web Text))

Max Activating Token Index: 169

Text #18

Max Range: 2.6003. Min Range: -2.6003

Max Act: 2.0936. Min Act: -0.0000

Data Index: 695108 (C4 (Web Text))

Max Activating Token Index: 292

Text #19

Max Range: 2.6003. Min Range: -2.6003

Max Act: 1.9694. Min Act: -0.0000

Data Index: 679838 (C4 (Web Text))

Max Activating Token Index: 251