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

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

Neuron 5357 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: 0.8061. Min Range: -0.8061

Max Act: 0.8061. Min Act: -0.0001

Data Index: 1612168 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.6969. Min Act: -0.0000

Data Index: 1554863 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.6122. Min Act: -0.0000

Data Index: 1630589 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.6039. Min Act: -0.0001

Data Index: 1576036 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.5481. Min Act: -0.0000

Data Index: 1569073 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.5504. Min Act: -0.0001

Data Index: 1566523 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.5441. Min Act: -0.0001

Data Index: 1566761 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.4923. Min Act: -0.0001

Data Index: 1630270 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.4425. Min Act: -0.0001

Data Index: 1594656 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.3966. Min Act: -0.0001

Data Index: 1621394 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.3351. Min Act: -0.0001

Data Index: 1569242 (Python Code)

Max Activating Token Index: 75

Text #11

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.3271. Min Act: -0.0001

Data Index: 1614029 (Python Code)

Max Activating Token Index: 134

Text #12

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.3217. Min Act: -0.0001

Data Index: 1564355 (Python Code)

Max Activating Token Index: 200

Text #13

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.3142. Min Act: -0.0001

Data Index: 1532508 (Python Code)

Max Activating Token Index: 368

Text #14

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.3195. Min Act: -0.0001

Data Index: 1393741 (Python Code)

Max Activating Token Index: 174

Text #15

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.3123. Min Act: -0.0001

Data Index: 1433057 (Python Code)

Max Activating Token Index: 283

Text #16

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.3110. Min Act: -0.0001

Data Index: 1456284 (Python Code)

Max Activating Token Index: 61

Text #17

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.3067. Min Act: -0.0001

Data Index: 1543299 (Python Code)

Max Activating Token Index: 110

Text #18

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.3069. Min Act: -0.0000

Data Index: 1598506 (Python Code)

Max Activating Token Index: 778

Text #19

Max Range: 0.8061. Min Range: -0.8061

Max Act: 0.3129. Min Act: -0.0000

Data Index: 1579695 (Python Code)

Max Activating Token Index: 1019