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

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

Neuron 4595 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: 2.1175. Min Range: -2.1175

Max Act: 2.1026. Min Act: -0.0002

Data Index: 365663 (C4 (Web Text))

Max Activating Token Index: 4

Text #1

Max Range: 2.1175. Min Range: -2.1175

Max Act: 2.1175. Min Act: -0.0002

Data Index: 966076 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 2.1175. Min Range: -2.1175

Max Act: 2.1175. Min Act: -0.0002

Data Index: 354993 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 2.1175. Min Range: -2.1175

Max Act: 2.1175. Min Act: -0.0002

Data Index: 124978 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 2.1175. Min Range: -2.1175

Max Act: 2.1057. Min Act: -0.0002

Data Index: 1190864 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 2.1175. Min Range: -2.1175

Max Act: 2.1057. Min Act: -0.0003

Data Index: 750218 (C4 (Web Text))

Max Activating Token Index: 2

Text #6

Max Range: 2.1175. Min Range: -2.1175

Max Act: 2.1057. Min Act: -0.0002

Data Index: 1214136 (C4 (Web Text))

Max Activating Token Index: 2

Text #7

Max Range: 2.1175. Min Range: -2.1175

Max Act: 2.1057. Min Act: -0.0002

Data Index: 731927 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 2.1175. Min Range: -2.1175

Max Act: 2.1057. Min Act: -0.0002

Data Index: 1233388 (C4 (Web Text))

Max Activating Token Index: 2

Text #9

Max Range: 2.1175. Min Range: -2.1175

Max Act: 2.1057. Min Act: -0.0002

Data Index: 487093 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 2.1175. Min Range: -2.1175

Max Act: 2.1057. Min Act: -0.0002

Data Index: 1339356 (C4 (Web Text))

Max Activating Token Index: 2

Text #11

Max Range: 2.1175. Min Range: -2.1175

Max Act: 2.1057. Min Act: -0.0003

Data Index: 537410 (C4 (Web Text))

Max Activating Token Index: 2

Text #12

Max Range: 2.1175. Min Range: -2.1175

Max Act: 2.1057. Min Act: -0.0002

Data Index: 634863 (C4 (Web Text))

Max Activating Token Index: 2

Text #13

Max Range: 2.1175. Min Range: -2.1175

Max Act: 1.9935. Min Act: -0.0002

Data Index: 824464 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 2.1175. Min Range: -2.1175

Max Act: 1.9677. Min Act: -0.0002

Data Index: 1152 (C4 (Web Text))

Max Activating Token Index: 3

Text #15

Max Range: 2.1175. Min Range: -2.1175

Max Act: 1.9502. Min Act: -0.0002

Data Index: 1006199 (C4 (Web Text))

Max Activating Token Index: 3

Text #16

Max Range: 2.1175. Min Range: -2.1175

Max Act: 1.8655. Min Act: -0.0002

Data Index: 538264 (C4 (Web Text))

Max Activating Token Index: 847

Text #17

Max Range: 2.1175. Min Range: -2.1175

Max Act: 1.8260. Min Act: -0.0002

Data Index: 157517 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 2.1175. Min Range: -2.1175

Max Act: 1.8347. Min Act: -0.0002

Data Index: 1310127 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 2.1175. Min Range: -2.1175

Max Act: 1.8120. Min Act: -0.0002

Data Index: 607441 (C4 (Web Text))

Max Activating Token Index: 633