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

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

Neuron 4035 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: 1.1135. Min Range: -1.1135

Max Act: 1.1135. Min Act: -0.0002

Data Index: 568846 (C4 (Web Text))

Max Activating Token Index: 950

Text #1

Max Range: 1.1135. Min Range: -1.1135

Max Act: 1.0617. Min Act: -0.0002

Data Index: 130991 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 1.1135. Min Range: -1.1135

Max Act: 1.0573. Min Act: -0.0002

Data Index: 1172453 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 1.1135. Min Range: -1.1135

Max Act: 1.0597. Min Act: -0.0002

Data Index: 123107 (C4 (Web Text))

Max Activating Token Index: 997

Text #4

Max Range: 1.1135. Min Range: -1.1135

Max Act: 1.0392. Min Act: -0.0002

Data Index: 1138714 (C4 (Web Text))

Max Activating Token Index: 502

Text #5

Max Range: 1.1135. Min Range: -1.1135

Max Act: 1.0571. Min Act: -0.0002

Data Index: 961938 (C4 (Web Text))

Max Activating Token Index: 591

Text #6

Max Range: 1.1135. Min Range: -1.1135

Max Act: 1.0393. Min Act: -0.0002

Data Index: 1002706 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 1.1135. Min Range: -1.1135

Max Act: 1.0356. Min Act: -0.0002

Data Index: 1236140 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 1.1135. Min Range: -1.1135

Max Act: 0.9936. Min Act: -0.0002

Data Index: 634717 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 1.1135. Min Range: -1.1135

Max Act: 1.0288. Min Act: -0.0002

Data Index: 1318954 (C4 (Web Text))

Max Activating Token Index: 746

Text #10

Max Range: 1.1135. Min Range: -1.1135

Max Act: 1.0168. Min Act: -0.0002

Data Index: 425444 (C4 (Web Text))

Max Activating Token Index: 445

Text #11

Max Range: 1.1135. Min Range: -1.1135

Max Act: 1.0155. Min Act: -0.0002

Data Index: 318704 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 1.1135. Min Range: -1.1135

Max Act: 1.0048. Min Act: -0.0002

Data Index: 467830 (C4 (Web Text))

Max Activating Token Index: 611

Text #13

Max Range: 1.1135. Min Range: -1.1135

Max Act: 1.0006. Min Act: -0.0002

Data Index: 160311 (C4 (Web Text))

Max Activating Token Index: 941

Text #14

Max Range: 1.1135. Min Range: -1.1135

Max Act: 0.9858. Min Act: -0.0002

Data Index: 716461 (C4 (Web Text))

Max Activating Token Index: 311

Text #15

Max Range: 1.1135. Min Range: -1.1135

Max Act: 0.9958. Min Act: -0.0002

Data Index: 138994 (C4 (Web Text))

Max Activating Token Index: 557

Text #16

Max Range: 1.1135. Min Range: -1.1135

Max Act: 0.9873. Min Act: -0.0003

Data Index: 1097208 (C4 (Web Text))

Max Activating Token Index: 346

Text #17

Max Range: 1.1135. Min Range: -1.1135

Max Act: 0.9726. Min Act: -0.0002

Data Index: 251835 (C4 (Web Text))

Max Activating Token Index: 337

Text #18

Max Range: 1.1135. Min Range: -1.1135

Max Act: 0.9809. Min Act: -0.0002

Data Index: 23223 (C4 (Web Text))

Max Activating Token Index: 601

Text #19

Max Range: 1.1135. Min Range: -1.1135

Max Act: 0.9640. Min Act: -0.0002

Data Index: 706282 (C4 (Web Text))

Max Activating Token Index: 451