Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2126 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4202. Min Range: -1.4202

Max Act: 1.4202. Min Act: -0.0000

Data Index: 931193 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 1.4202. Min Range: -1.4202

Max Act: 1.2129. Min Act: -0.0000

Data Index: 548152 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 1.4202. Min Range: -1.4202

Max Act: 0.9953. Min Act: -0.0000

Data Index: 275358 (C4 (Web Text))

Max Activating Token Index: 301

Text #3

Max Range: 1.4202. Min Range: -1.4202

Max Act: 0.9362. Min Act: -0.0000

Data Index: 1204507 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 1.4202. Min Range: -1.4202

Max Act: 1.1580. Min Act: -0.0000

Data Index: 1278966 (C4 (Web Text))

Max Activating Token Index: 289

Text #5

Max Range: 1.4202. Min Range: -1.4202

Max Act: 0.8191. Min Act: -0.0000

Data Index: 1118081 (C4 (Web Text))

Max Activating Token Index: 439

Text #6

Max Range: 1.4202. Min Range: -1.4202

Max Act: 0.8571. Min Act: -0.0000

Data Index: 307327 (C4 (Web Text))

Max Activating Token Index: 211

Text #7

Max Range: 1.4202. Min Range: -1.4202

Max Act: 0.7464. Min Act: -0.0000

Data Index: 559343 (C4 (Web Text))

Max Activating Token Index: 377

Text #8

Max Range: 1.4202. Min Range: -1.4202

Max Act: 0.7265. Min Act: -0.0000

Data Index: 26252 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 1.4202. Min Range: -1.4202

Max Act: 0.5142. Min Act: -0.0000

Data Index: 1012932 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 1.4202. Min Range: -1.4202

Max Act: 0.4933. Min Act: -0.0000

Data Index: 1301113 (C4 (Web Text))

Max Activating Token Index: 740

Text #11

Max Range: 1.4202. Min Range: -1.4202

Max Act: 0.4945. Min Act: -0.0000

Data Index: 1993 (C4 (Web Text))

Max Activating Token Index: 552

Text #12

Max Range: 1.4202. Min Range: -1.4202

Max Act: 0.5265. Min Act: -0.0000

Data Index: 853285 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 1.4202. Min Range: -1.4202

Max Act: 0.5086. Min Act: -0.0000

Data Index: 1244014 (C4 (Web Text))

Max Activating Token Index: 248

Text #14

Max Range: 1.4202. Min Range: -1.4202

Max Act: 0.4418. Min Act: -0.0000

Data Index: 1087301 (C4 (Web Text))

Max Activating Token Index: 528

Text #15

Max Range: 1.4202. Min Range: -1.4202

Max Act: 0.4008. Min Act: -0.0000

Data Index: 505854 (C4 (Web Text))

Max Activating Token Index: 989

Text #16

Max Range: 1.4202. Min Range: -1.4202

Max Act: 0.4335. Min Act: -0.0000

Data Index: 597266 (C4 (Web Text))

Max Activating Token Index: 548

Text #17

Max Range: 1.4202. Min Range: -1.4202

Max Act: 0.4198. Min Act: -0.0000

Data Index: 1192595 (C4 (Web Text))

Max Activating Token Index: 468

Text #18

Max Range: 1.4202. Min Range: -1.4202

Max Act: 0.4047. Min Act: -0.0000

Data Index: 407607 (C4 (Web Text))

Max Activating Token Index: 922

Text #19

Max Range: 1.4202. Min Range: -1.4202

Max Act: 0.3862. Min Act: -0.0000

Data Index: 1321445 (C4 (Web Text))

Max Activating Token Index: 790