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

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

Neuron 5678 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2275. Min Range: -1.2275

Max Act: 1.2275. Min Act: -0.0000

Data Index: 460959 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 1.2275. Min Range: -1.2275

Max Act: 1.0272. Min Act: -0.0000

Data Index: 491084 (C4 (Web Text))

Max Activating Token Index: 332

Text #2

Max Range: 1.2275. Min Range: -1.2275

Max Act: 1.1003. Min Act: -0.0000

Data Index: 233026 (C4 (Web Text))

Max Activating Token Index: 110

Text #3

Max Range: 1.2275. Min Range: -1.2275

Max Act: 1.1340. Min Act: -0.0000

Data Index: 597292 (C4 (Web Text))

Max Activating Token Index: 176

Text #4

Max Range: 1.2275. Min Range: -1.2275

Max Act: 1.0612. Min Act: -0.0000

Data Index: 20105 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 1.2275. Min Range: -1.2275

Max Act: 1.0782. Min Act: -0.0000

Data Index: 1158900 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 1.2275. Min Range: -1.2275

Max Act: 1.0024. Min Act: -0.0000

Data Index: 1157206 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 1.2275. Min Range: -1.2275

Max Act: 1.0449. Min Act: -0.0000

Data Index: 18336 (C4 (Web Text))

Max Activating Token Index: 882

Text #8

Max Range: 1.2275. Min Range: -1.2275

Max Act: 1.0353. Min Act: -0.0000

Data Index: 128232 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.9947. Min Act: -0.0000

Data Index: 1274635 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 1.2275. Min Range: -1.2275

Max Act: 1.0305. Min Act: -0.0000

Data Index: 1055662 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 1.2275. Min Range: -1.2275

Max Act: 1.0477. Min Act: -0.0000

Data Index: 861567 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 1.2275. Min Range: -1.2275

Max Act: 1.0338. Min Act: -0.0000

Data Index: 988687 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.9675. Min Act: -0.0000

Data Index: 998081 (C4 (Web Text))

Max Activating Token Index: 295

Text #14

Max Range: 1.2275. Min Range: -1.2275

Max Act: 1.0168. Min Act: -0.0000

Data Index: 215027 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.9876. Min Act: -0.0000

Data Index: 1039722 (C4 (Web Text))

Max Activating Token Index: 241

Text #16

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.9383. Min Act: -0.0000

Data Index: 571246 (C4 (Web Text))

Max Activating Token Index: 369

Text #17

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.9765. Min Act: -0.0000

Data Index: 905831 (C4 (Web Text))

Max Activating Token Index: 135

Text #18

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.9808. Min Act: -0.0000

Data Index: 1258013 (C4 (Web Text))

Max Activating Token Index: 163

Text #19

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.9500. Min Act: -0.0000

Data Index: 560890 (C4 (Web Text))

Max Activating Token Index: 662