Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 455 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.6832. Min Act: -0.0001

Data Index: 597009 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.6219. Min Act: -0.0001

Data Index: 1029506 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.5560. Min Act: -0.0001

Data Index: 1330289 (C4 (Web Text))

Max Activating Token Index: 276

Text #3

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.5203. Min Act: -0.0001

Data Index: 652963 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.5569. Min Act: -0.0001

Data Index: 25055 (C4 (Web Text))

Max Activating Token Index: 452

Text #5

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.5381. Min Act: -0.0001

Data Index: 924609 (C4 (Web Text))

Max Activating Token Index: 444

Text #6

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.5713. Min Act: -0.0001

Data Index: 1156441 (C4 (Web Text))

Max Activating Token Index: 428

Text #7

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.5593. Min Act: -0.0001

Data Index: 703719 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.5211. Min Act: -0.0001

Data Index: 499156 (C4 (Web Text))

Max Activating Token Index: 390

Text #9

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.5119. Min Act: -0.0001

Data Index: 1277704 (C4 (Web Text))

Max Activating Token Index: 418

Text #10

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.5047. Min Act: -0.0001

Data Index: 530451 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.4824. Min Act: -0.0001

Data Index: 375204 (C4 (Web Text))

Max Activating Token Index: 271

Text #12

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.5107. Min Act: -0.0001

Data Index: 877704 (C4 (Web Text))

Max Activating Token Index: 292

Text #13

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.4978. Min Act: -0.0001

Data Index: 313681 (C4 (Web Text))

Max Activating Token Index: 433

Text #14

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.5086. Min Act: -0.0001

Data Index: 34931 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.4960. Min Act: -0.0001

Data Index: 608659 (C4 (Web Text))

Max Activating Token Index: 191

Text #16

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.4964. Min Act: -0.0001

Data Index: 1286801 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.4872. Min Act: -0.0001

Data Index: 231484 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.4778. Min Act: -0.0001

Data Index: 1244575 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 0.6832. Min Range: -0.6832

Max Act: 0.4643. Min Act: -0.0001

Data Index: 464270 (C4 (Web Text))

Max Activating Token Index: 64