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

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

Neuron 4342 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9029. Min Range: -0.9029

Max Act: 0.8720. Min Act: -0.0000

Data Index: 1210521 (C4 (Web Text))

Max Activating Token Index: 658

Text #1

Max Range: 0.9029. Min Range: -0.9029

Max Act: 0.9029. Min Act: -0.0000

Data Index: 1285988 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 0.9029. Min Range: -0.9029

Max Act: 0.8622. Min Act: -0.0000

Data Index: 363192 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 0.9029. Min Range: -0.9029

Max Act: 0.8138. Min Act: -0.0001

Data Index: 194051 (C4 (Web Text))

Max Activating Token Index: 132

Text #4

Max Range: 0.9029. Min Range: -0.9029

Max Act: 0.8400. Min Act: -0.0000

Data Index: 884127 (C4 (Web Text))

Max Activating Token Index: 446

Text #5

Max Range: 0.9029. Min Range: -0.9029

Max Act: 0.7404. Min Act: -0.0000

Data Index: 670884 (C4 (Web Text))

Max Activating Token Index: 505

Text #6

Max Range: 0.9029. Min Range: -0.9029

Max Act: 0.7820. Min Act: -0.0000

Data Index: 1054475 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 0.9029. Min Range: -0.9029

Max Act: 0.7350. Min Act: -0.0000

Data Index: 595023 (C4 (Web Text))

Max Activating Token Index: 358

Text #8

Max Range: 0.9029. Min Range: -0.9029

Max Act: 0.7824. Min Act: -0.0000

Data Index: 313892 (C4 (Web Text))

Max Activating Token Index: 761

Text #9

Max Range: 0.9029. Min Range: -0.9029

Max Act: 0.7309. Min Act: -0.0000

Data Index: 763319 (C4 (Web Text))

Max Activating Token Index: 942

Text #10

Max Range: 0.9029. Min Range: -0.9029

Max Act: 0.7423. Min Act: -0.0000

Data Index: 669145 (C4 (Web Text))

Max Activating Token Index: 587

Text #11

Max Range: 0.9029. Min Range: -0.9029

Max Act: 0.7423. Min Act: -0.0000

Data Index: 9136 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 0.9029. Min Range: -0.9029

Max Act: 0.7696. Min Act: -0.0000

Data Index: 804666 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 0.9029. Min Range: -0.9029

Max Act: 0.7194. Min Act: -0.0000

Data Index: 70926 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 0.9029. Min Range: -0.9029

Max Act: 0.6991. Min Act: -0.0000

Data Index: 125890 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 0.9029. Min Range: -0.9029

Max Act: 0.7306. Min Act: -0.0000

Data Index: 1149800 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 0.9029. Min Range: -0.9029

Max Act: 0.6904. Min Act: -0.0000

Data Index: 971285 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 0.9029. Min Range: -0.9029

Max Act: 0.7105. Min Act: -0.0000

Data Index: 221220 (C4 (Web Text))

Max Activating Token Index: 257

Text #18

Max Range: 0.9029. Min Range: -0.9029

Max Act: 0.6546. Min Act: -0.0000

Data Index: 517838 (C4 (Web Text))

Max Activating Token Index: 177

Text #19

Max Range: 0.9029. Min Range: -0.9029

Max Act: 0.6595. Min Act: -0.0001

Data Index: 886548 (C4 (Web Text))

Max Activating Token Index: 289