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

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

Neuron 2564 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1395. Min Act: -0.0000

Data Index: 1251347 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1297. Min Act: -0.0001

Data Index: 108752 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1213. Min Act: -0.0001

Data Index: 1066728 (C4 (Web Text))

Max Activating Token Index: 748

Text #3

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1175. Min Act: -0.0000

Data Index: 783337 (C4 (Web Text))

Max Activating Token Index: 387

Text #4

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1121. Min Act: -0.0000

Data Index: 1333763 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1067. Min Act: -0.0001

Data Index: 438985 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1099. Min Act: -0.0001

Data Index: 492399 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1060. Min Act: -0.0001

Data Index: 1256591 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1003. Min Act: -0.0001

Data Index: 566721 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1096. Min Act: -0.0000

Data Index: 294711 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1052. Min Act: -0.0001

Data Index: 313652 (C4 (Web Text))

Max Activating Token Index: 270

Text #11

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1019. Min Act: -0.0000

Data Index: 636999 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0944. Min Act: -0.0001

Data Index: 1295104 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0972. Min Act: -0.0001

Data Index: 325052 (C4 (Web Text))

Max Activating Token Index: 120

Text #14

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0964. Min Act: -0.0001

Data Index: 670271 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1037. Min Act: -0.0001

Data Index: 741956 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0996. Min Act: -0.0001

Data Index: 690898 (C4 (Web Text))

Max Activating Token Index: 204

Text #17

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0985. Min Act: -0.0001

Data Index: 90873 (C4 (Web Text))

Max Activating Token Index: 335

Text #18

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1022. Min Act: -0.0001

Data Index: 706613 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0961. Min Act: -0.0001

Data Index: 1262514 (C4 (Web Text))

Max Activating Token Index: 916