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

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

Neuron 1968 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: 2.6232. Min Range: -2.6232

Max Act: 2.6232. Min Act: -0.0000

Data Index: 57809 (C4 (Web Text))

Max Activating Token Index: 666

Text #1

Max Range: 2.6232. Min Range: -2.6232

Max Act: 2.2605. Min Act: -0.0000

Data Index: 434217 (C4 (Web Text))

Max Activating Token Index: 182

Text #2

Max Range: 2.6232. Min Range: -2.6232

Max Act: 2.1858. Min Act: -0.0000

Data Index: 1025912 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 2.6232. Min Range: -2.6232

Max Act: 2.0590. Min Act: -0.0000

Data Index: 391498 (C4 (Web Text))

Max Activating Token Index: 437

Text #4

Max Range: 2.6232. Min Range: -2.6232

Max Act: 1.9959. Min Act: -0.0000

Data Index: 1355417 (C4 (Web Text))

Max Activating Token Index: 318

Text #5

Max Range: 2.6232. Min Range: -2.6232

Max Act: 1.7437. Min Act: -0.0000

Data Index: 76827 (C4 (Web Text))

Max Activating Token Index: 98

Text #6

Max Range: 2.6232. Min Range: -2.6232

Max Act: 1.7284. Min Act: -0.0000

Data Index: 472623 (C4 (Web Text))

Max Activating Token Index: 539

Text #7

Max Range: 2.6232. Min Range: -2.6232

Max Act: 1.7064. Min Act: -0.0000

Data Index: 745736 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 2.6232. Min Range: -2.6232

Max Act: 1.9035. Min Act: -0.0000

Data Index: 785361 (C4 (Web Text))

Max Activating Token Index: 931

Text #9

Max Range: 2.6232. Min Range: -2.6232

Max Act: 1.8009. Min Act: -0.0000

Data Index: 205337 (C4 (Web Text))

Max Activating Token Index: 888

Text #10

Max Range: 2.6232. Min Range: -2.6232

Max Act: 1.7778. Min Act: -0.0000

Data Index: 883697 (C4 (Web Text))

Max Activating Token Index: 666

Text #11

Max Range: 2.6232. Min Range: -2.6232

Max Act: 1.7595. Min Act: -0.0000

Data Index: 440223 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 2.6232. Min Range: -2.6232

Max Act: 1.7396. Min Act: -0.0000

Data Index: 1228021 (C4 (Web Text))

Max Activating Token Index: 909

Text #13

Max Range: 2.6232. Min Range: -2.6232

Max Act: 1.7381. Min Act: -0.0000

Data Index: 1381282 (Python Code)

Max Activating Token Index: 218

Text #14

Max Range: 2.6232. Min Range: -2.6232

Max Act: 1.7308. Min Act: -0.0000

Data Index: 715140 (C4 (Web Text))

Max Activating Token Index: 914

Text #15

Max Range: 2.6232. Min Range: -2.6232

Max Act: 1.7093. Min Act: -0.0000

Data Index: 904084 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 2.6232. Min Range: -2.6232

Max Act: 1.6967. Min Act: -0.0000

Data Index: 1452465 (Python Code)

Max Activating Token Index: 541

Text #17

Max Range: 2.6232. Min Range: -2.6232

Max Act: 1.8645. Min Act: -0.0000

Data Index: 605182 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 2.6232. Min Range: -2.6232

Max Act: 1.6518. Min Act: -0.0000

Data Index: 1144788 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 2.6232. Min Range: -2.6232

Max Act: 1.5685. Min Act: -0.0000

Data Index: 1489813 (Python Code)

Max Activating Token Index: 135