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

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

Neuron 4212 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8266. Min Range: -0.8266

Max Act: 0.8266. Min Act: -0.0000

Data Index: 209623 (C4 (Web Text))

Max Activating Token Index: 442

Text #1

Max Range: 0.8266. Min Range: -0.8266

Max Act: 0.6584. Min Act: -0.0000

Data Index: 673894 (C4 (Web Text))

Max Activating Token Index: 491

Text #2

Max Range: 0.8266. Min Range: -0.8266

Max Act: 0.5524. Min Act: -0.0000

Data Index: 101892 (C4 (Web Text))

Max Activating Token Index: 236

Text #3

Max Range: 0.8266. Min Range: -0.8266

Max Act: 0.6375. Min Act: -0.0000

Data Index: 1285224 (C4 (Web Text))

Max Activating Token Index: 483

Text #4

Max Range: 0.8266. Min Range: -0.8266

Max Act: 0.5998. Min Act: -0.0000

Data Index: 471760 (C4 (Web Text))

Max Activating Token Index: 302

Text #5

Max Range: 0.8266. Min Range: -0.8266

Max Act: 0.5411. Min Act: -0.0000

Data Index: 571736 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 0.8266. Min Range: -0.8266

Max Act: 0.5510. Min Act: -0.0000

Data Index: 1188106 (C4 (Web Text))

Max Activating Token Index: 801

Text #7

Max Range: 0.8266. Min Range: -0.8266

Max Act: 0.4933. Min Act: -0.0000

Data Index: 911586 (C4 (Web Text))

Max Activating Token Index: 568

Text #8

Max Range: 0.8266. Min Range: -0.8266

Max Act: 0.5776. Min Act: -0.0000

Data Index: 51203 (C4 (Web Text))

Max Activating Token Index: 538

Text #9

Max Range: 0.8266. Min Range: -0.8266

Max Act: 0.5481. Min Act: -0.0000

Data Index: 146532 (C4 (Web Text))

Max Activating Token Index: 966

Text #10

Max Range: 0.8266. Min Range: -0.8266

Max Act: 0.5140. Min Act: -0.0000

Data Index: 361009 (C4 (Web Text))

Max Activating Token Index: 314

Text #11

Max Range: 0.8266. Min Range: -0.8266

Max Act: 0.5033. Min Act: -0.0000

Data Index: 1085710 (C4 (Web Text))

Max Activating Token Index: 313

Text #12

Max Range: 0.8266. Min Range: -0.8266

Max Act: 0.5652. Min Act: -0.0000

Data Index: 616919 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 0.8266. Min Range: -0.8266

Max Act: 0.5422. Min Act: -0.0000

Data Index: 505591 (C4 (Web Text))

Max Activating Token Index: 335

Text #14

Max Range: 0.8266. Min Range: -0.8266

Max Act: 0.5291. Min Act: -0.0000

Data Index: 512517 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 0.8266. Min Range: -0.8266

Max Act: 0.5097. Min Act: -0.0000

Data Index: 203971 (C4 (Web Text))

Max Activating Token Index: 102

Text #16

Max Range: 0.8266. Min Range: -0.8266

Max Act: 0.5778. Min Act: -0.0000

Data Index: 433752 (C4 (Web Text))

Max Activating Token Index: 207

Text #17

Max Range: 0.8266. Min Range: -0.8266

Max Act: 0.5327. Min Act: -0.0000

Data Index: 18408 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 0.8266. Min Range: -0.8266

Max Act: 0.5433. Min Act: -0.0000

Data Index: 493320 (C4 (Web Text))

Max Activating Token Index: 287

Text #19

Max Range: 0.8266. Min Range: -0.8266

Max Act: 0.5022. Min Act: -0.0000

Data Index: 688352 (C4 (Web Text))

Max Activating Token Index: 858