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

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

Neuron 4847 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0206. Min Range: -3.0206

Max Act: 3.0206. Min Act: -0.0000

Data Index: 560087 (C4 (Web Text))

Max Activating Token Index: 615

Text #1

Max Range: 3.0206. Min Range: -3.0206

Max Act: 2.8132. Min Act: -0.0000

Data Index: 880107 (C4 (Web Text))

Max Activating Token Index: 478

Text #2

Max Range: 3.0206. Min Range: -3.0206

Max Act: 2.6653. Min Act: -0.0000

Data Index: 1318002 (C4 (Web Text))

Max Activating Token Index: 547

Text #3

Max Range: 3.0206. Min Range: -3.0206

Max Act: 2.2208. Min Act: -0.0000

Data Index: 1297418 (C4 (Web Text))

Max Activating Token Index: 107

Text #4

Max Range: 3.0206. Min Range: -3.0206

Max Act: 2.0605. Min Act: -0.0000

Data Index: 1293460 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 3.0206. Min Range: -3.0206

Max Act: 2.1203. Min Act: -0.0000

Data Index: 1291581 (C4 (Web Text))

Max Activating Token Index: 273

Text #6

Max Range: 3.0206. Min Range: -3.0206

Max Act: 1.8459. Min Act: -0.0000

Data Index: 139023 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 3.0206. Min Range: -3.0206

Max Act: 1.9193. Min Act: -0.0000

Data Index: 132041 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 3.0206. Min Range: -3.0206

Max Act: 1.8210. Min Act: -0.0000

Data Index: 933588 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 3.0206. Min Range: -3.0206

Max Act: 1.7826. Min Act: -0.0000

Data Index: 119519 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 3.0206. Min Range: -3.0206

Max Act: 1.7684. Min Act: -0.0000

Data Index: 487675 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 3.0206. Min Range: -3.0206

Max Act: 1.7371. Min Act: -0.0000

Data Index: 930291 (C4 (Web Text))

Max Activating Token Index: 792

Text #12

Max Range: 3.0206. Min Range: -3.0206

Max Act: 1.6353. Min Act: -0.0000

Data Index: 1096539 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 3.0206. Min Range: -3.0206

Max Act: 1.8077. Min Act: -0.0000

Data Index: 991438 (C4 (Web Text))

Max Activating Token Index: 909

Text #14

Max Range: 3.0206. Min Range: -3.0206

Max Act: 1.7045. Min Act: -0.0000

Data Index: 922376 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 3.0206. Min Range: -3.0206

Max Act: 1.5982. Min Act: -0.0000

Data Index: 658211 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 3.0206. Min Range: -3.0206

Max Act: 1.5976. Min Act: -0.0000

Data Index: 695994 (C4 (Web Text))

Max Activating Token Index: 1021

Text #17

Max Range: 3.0206. Min Range: -3.0206

Max Act: 1.7949. Min Act: -0.0000

Data Index: 233504 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 3.0206. Min Range: -3.0206

Max Act: 1.6347. Min Act: -0.0000

Data Index: 1236257 (C4 (Web Text))

Max Activating Token Index: 712

Text #19

Max Range: 3.0206. Min Range: -3.0206

Max Act: 1.6257. Min Act: -0.0000

Data Index: 1244702 (C4 (Web Text))

Max Activating Token Index: 438