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

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

Neuron 4212 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: 0.0028. Min Range: -0.0028

Max Act: 0.0028. Min Act: -0.0001

Data Index: 405700 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0028. Min Act: -0.0001

Data Index: 745484 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0027. Min Act: -0.0001

Data Index: 1403831 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0026. Min Act: -0.0001

Data Index: 1375880 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0025. Min Act: -0.0001

Data Index: 1531548 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0024. Min Act: -0.0001

Data Index: 1642192 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0024. Min Act: -0.0001

Data Index: 1560687 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0024. Min Act: -0.0001

Data Index: 303135 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0023. Min Act: -0.0001

Data Index: 415246 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0023. Min Act: -0.0001

Data Index: 864944 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0023. Min Act: -0.0001

Data Index: 1128285 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0023. Min Act: -0.0001

Data Index: 124947 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0022. Min Act: -0.0001

Data Index: 1115278 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0022. Min Act: -0.0001

Data Index: 288088 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0022. Min Act: -0.0001

Data Index: 1583759 (Python Code)

Max Activating Token Index: 339

Text #15

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0022. Min Act: -0.0001

Data Index: 1286296 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0021. Min Act: -0.0001

Data Index: 411950 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0021. Min Act: -0.0001

Data Index: 737122 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0021. Min Act: -0.0001

Data Index: 1234532 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0028. Min Range: -0.0028

Max Act: 0.0021. Min Act: -0.0001

Data Index: 314148 (C4 (Web Text))

Max Activating Token Index: 1023