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

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

Neuron 4034 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: 0.0178. Min Range: -0.0178

Max Act: 0.0178. Min Act: -0.0001

Data Index: 1473511 (Python Code)

Max Activating Token Index: 206

Text #1

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0175. Min Act: -0.0001

Data Index: 42679 (C4 (Web Text))

Max Activating Token Index: 843

Text #2

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0173. Min Act: -0.0001

Data Index: 453475 (C4 (Web Text))

Max Activating Token Index: 760

Text #3

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0168. Min Act: -0.0001

Data Index: 704846 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0167. Min Act: -0.0001

Data Index: 1532709 (Python Code)

Max Activating Token Index: 878

Text #5

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0167. Min Act: -0.0001

Data Index: 130175 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0163. Min Act: -0.0001

Data Index: 566983 (C4 (Web Text))

Max Activating Token Index: 987

Text #7

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0166. Min Act: -0.0001

Data Index: 948368 (C4 (Web Text))

Max Activating Token Index: 907

Text #8

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0167. Min Act: -0.0001

Data Index: 493191 (C4 (Web Text))

Max Activating Token Index: 508

Text #9

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0164. Min Act: -0.0001

Data Index: 1596222 (Python Code)

Max Activating Token Index: 146

Text #10

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0166. Min Act: -0.0001

Data Index: 899286 (C4 (Web Text))

Max Activating Token Index: 1011

Text #11

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0162. Min Act: -0.0001

Data Index: 45554 (C4 (Web Text))

Max Activating Token Index: 300

Text #12

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0163. Min Act: -0.0001

Data Index: 344383 (C4 (Web Text))

Max Activating Token Index: 247

Text #13

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0166. Min Act: -0.0001

Data Index: 1591058 (Python Code)

Max Activating Token Index: 52

Text #14

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0163. Min Act: -0.0001

Data Index: 652041 (C4 (Web Text))

Max Activating Token Index: 614

Text #15

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0164. Min Act: -0.0001

Data Index: 414530 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0162. Min Act: -0.0001

Data Index: 1466733 (Python Code)

Max Activating Token Index: 714

Text #17

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0161. Min Act: -0.0001

Data Index: 203492 (C4 (Web Text))

Max Activating Token Index: 619

Text #18

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0164. Min Act: -0.0001

Data Index: 144494 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0161. Min Act: -0.0001

Data Index: 1109566 (C4 (Web Text))

Max Activating Token Index: 312