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

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

Neuron 271 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: 3.3740. Min Range: -3.3740

Max Act: 3.3740. Min Act: -0.0000

Data Index: 30512 (C4 (Web Text))

Max Activating Token Index: 343

Text #1

Max Range: 3.3740. Min Range: -3.3740

Max Act: 2.7917. Min Act: -0.0000

Data Index: 937282 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 3.3740. Min Range: -3.3740

Max Act: 2.7302. Min Act: -0.0001

Data Index: 1347281 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 3.3740. Min Range: -3.3740

Max Act: 2.6316. Min Act: -0.0001

Data Index: 973630 (C4 (Web Text))

Max Activating Token Index: 153

Text #4

Max Range: 3.3740. Min Range: -3.3740

Max Act: 2.4612. Min Act: -0.0001

Data Index: 520666 (C4 (Web Text))

Max Activating Token Index: 622

Text #5

Max Range: 3.3740. Min Range: -3.3740

Max Act: 2.4029. Min Act: -0.0000

Data Index: 121965 (C4 (Web Text))

Max Activating Token Index: 230

Text #6

Max Range: 3.3740. Min Range: -3.3740

Max Act: 2.2821. Min Act: -0.0001

Data Index: 18658 (C4 (Web Text))

Max Activating Token Index: 1001

Text #7

Max Range: 3.3740. Min Range: -3.3740

Max Act: 2.2499. Min Act: -0.0001

Data Index: 396272 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 3.3740. Min Range: -3.3740

Max Act: 2.2399. Min Act: -0.0001

Data Index: 1329278 (C4 (Web Text))

Max Activating Token Index: 750

Text #9

Max Range: 3.3740. Min Range: -3.3740

Max Act: 2.2454. Min Act: -0.0001

Data Index: 1059851 (C4 (Web Text))

Max Activating Token Index: 173

Text #10

Max Range: 3.3740. Min Range: -3.3740

Max Act: 1.9072. Min Act: -0.0001

Data Index: 1194430 (C4 (Web Text))

Max Activating Token Index: 291

Text #11

Max Range: 3.3740. Min Range: -3.3740

Max Act: 2.0082. Min Act: -0.0000

Data Index: 795728 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 3.3740. Min Range: -3.3740

Max Act: 1.8919. Min Act: -0.0000

Data Index: 469113 (C4 (Web Text))

Max Activating Token Index: 287

Text #13

Max Range: 3.3740. Min Range: -3.3740

Max Act: 1.9795. Min Act: -0.0001

Data Index: 306029 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 3.3740. Min Range: -3.3740

Max Act: 1.9051. Min Act: -0.0001

Data Index: 58073 (C4 (Web Text))

Max Activating Token Index: 371

Text #15

Max Range: 3.3740. Min Range: -3.3740

Max Act: 2.1606. Min Act: -0.0001

Data Index: 1287290 (C4 (Web Text))

Max Activating Token Index: 297

Text #16

Max Range: 3.3740. Min Range: -3.3740

Max Act: 1.9152. Min Act: -0.0000

Data Index: 982183 (C4 (Web Text))

Max Activating Token Index: 988

Text #17

Max Range: 3.3740. Min Range: -3.3740

Max Act: 1.9143. Min Act: -0.0001

Data Index: 399170 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 3.3740. Min Range: -3.3740

Max Act: 1.8458. Min Act: -0.0001

Data Index: 58272 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 3.3740. Min Range: -3.3740

Max Act: 1.6411. Min Act: -0.0000

Data Index: 231224 (C4 (Web Text))

Max Activating Token Index: 121