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

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

Neuron 6019 in Layer 0

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: 1.0088. Min Range: -1.0088

Max Act: 1.0088. Min Act: -0.0001

Data Index: 1124699 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.9987. Min Act: -0.0001

Data Index: 462892 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.9798. Min Act: -0.0001

Data Index: 826537 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.9596. Min Act: -0.0001

Data Index: 799390 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.9567. Min Act: -0.0001

Data Index: 410691 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.9488. Min Act: -0.0001

Data Index: 859740 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.9583. Min Act: -0.0001

Data Index: 792817 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.9584. Min Act: -0.0001

Data Index: 206679 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.9310. Min Act: -0.0001

Data Index: 138058 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.9402. Min Act: -0.0001

Data Index: 622054 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.9487. Min Act: -0.0001

Data Index: 1250244 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.9545. Min Act: -0.0001

Data Index: 529626 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.9322. Min Act: -0.0001

Data Index: 1015553 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.9279. Min Act: -0.0001

Data Index: 662357 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.9423. Min Act: -0.0001

Data Index: 25548 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.9337. Min Act: -0.0001

Data Index: 751806 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.9186. Min Act: -0.0001

Data Index: 276424 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.9172. Min Act: -0.0001

Data Index: 260926 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.9270. Min Act: -0.0001

Data Index: 1205923 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 1.0088. Min Range: -1.0088

Max Act: 0.9340. Min Act: -0.0001

Data Index: 1010903 (C4 (Web Text))

Max Activating Token Index: 1023