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

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

Neuron 1770 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.5636. Min Range: -1.5636

Max Act: 1.5636. Min Act: -0.0002

Data Index: 196585 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 1.5636. Min Range: -1.5636

Max Act: 1.4528. Min Act: -0.0002

Data Index: 1416114 (Python Code)

Max Activating Token Index: 795

Text #2

Max Range: 1.5636. Min Range: -1.5636

Max Act: 1.4848. Min Act: -0.0002

Data Index: 1435030 (Python Code)

Max Activating Token Index: 389

Text #3

Max Range: 1.5636. Min Range: -1.5636

Max Act: 1.4215. Min Act: -0.0002

Data Index: 379953 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 1.5636. Min Range: -1.5636

Max Act: 1.4262. Min Act: -0.0002

Data Index: 902908 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 1.5636. Min Range: -1.5636

Max Act: 1.4506. Min Act: -0.0002

Data Index: 514617 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 1.5636. Min Range: -1.5636

Max Act: 1.4216. Min Act: -0.0002

Data Index: 1383055 (Python Code)

Max Activating Token Index: 784

Text #7

Max Range: 1.5636. Min Range: -1.5636

Max Act: 1.4051. Min Act: -0.0002

Data Index: 752317 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 1.5636. Min Range: -1.5636

Max Act: 1.3559. Min Act: -0.0002

Data Index: 1366745 (Python Code)

Max Activating Token Index: 3

Text #9

Max Range: 1.5636. Min Range: -1.5636

Max Act: 1.3559. Min Act: -0.0002

Data Index: 1498067 (Python Code)

Max Activating Token Index: 3

Text #10

Max Range: 1.5636. Min Range: -1.5636

Max Act: 1.3460. Min Act: -0.0002

Data Index: 1545745 (Python Code)

Max Activating Token Index: 880

Text #11

Max Range: 1.5636. Min Range: -1.5636

Max Act: 1.3873. Min Act: -0.0002

Data Index: 1135463 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 1.5636. Min Range: -1.5636

Max Act: 1.3302. Min Act: -0.0002

Data Index: 1374422 (Python Code)

Max Activating Token Index: 445

Text #13

Max Range: 1.5636. Min Range: -1.5636

Max Act: 1.3757. Min Act: -0.0002

Data Index: 991867 (C4 (Web Text))

Max Activating Token Index: 205

Text #14

Max Range: 1.5636. Min Range: -1.5636

Max Act: 1.3271. Min Act: -0.0002

Data Index: 1519808 (Python Code)

Max Activating Token Index: 750

Text #15

Max Range: 1.5636. Min Range: -1.5636

Max Act: 1.2922. Min Act: -0.0002

Data Index: 1446288 (Python Code)

Max Activating Token Index: 235

Text #16

Max Range: 1.5636. Min Range: -1.5636

Max Act: 1.3519. Min Act: -0.0002

Data Index: 1192940 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 1.5636. Min Range: -1.5636

Max Act: 1.2872. Min Act: -0.0002

Data Index: 1596180 (Python Code)

Max Activating Token Index: 208

Text #18

Max Range: 1.5636. Min Range: -1.5636

Max Act: 1.3562. Min Act: -0.0002

Data Index: 355563 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 1.5636. Min Range: -1.5636

Max Act: 1.3293. Min Act: -0.0002

Data Index: 1558948 (Python Code)

Max Activating Token Index: 57