Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3396 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4085. Min Range: -1.4085

Max Act: 1.3570. Min Act: -0.0001

Data Index: 1235905 (C4 (Web Text))

Max Activating Token Index: 992

Text #1

Max Range: 1.4085. Min Range: -1.4085

Max Act: 1.4085. Min Act: -0.0001

Data Index: 1797 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 1.4085. Min Range: -1.4085

Max Act: 1.3371. Min Act: -0.0001

Data Index: 1108740 (C4 (Web Text))

Max Activating Token Index: 589

Text #3

Max Range: 1.4085. Min Range: -1.4085

Max Act: 1.3566. Min Act: -0.0001

Data Index: 710521 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 1.4085. Min Range: -1.4085

Max Act: 1.3119. Min Act: -0.0001

Data Index: 1001452 (C4 (Web Text))

Max Activating Token Index: 919

Text #5

Max Range: 1.4085. Min Range: -1.4085

Max Act: 1.3955. Min Act: -0.0001

Data Index: 813903 (C4 (Web Text))

Max Activating Token Index: 861

Text #6

Max Range: 1.4085. Min Range: -1.4085

Max Act: 1.2892. Min Act: -0.0001

Data Index: 381530 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 1.4085. Min Range: -1.4085

Max Act: 1.3240. Min Act: -0.0001

Data Index: 1087830 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 1.4085. Min Range: -1.4085

Max Act: 1.3067. Min Act: -0.0001

Data Index: 648560 (C4 (Web Text))

Max Activating Token Index: 841

Text #9

Max Range: 1.4085. Min Range: -1.4085

Max Act: 1.2255. Min Act: -0.0001

Data Index: 1325753 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 1.4085. Min Range: -1.4085

Max Act: 1.3324. Min Act: -0.0001

Data Index: 951603 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 1.4085. Min Range: -1.4085

Max Act: 1.2412. Min Act: -0.0001

Data Index: 352322 (C4 (Web Text))

Max Activating Token Index: 343

Text #12

Max Range: 1.4085. Min Range: -1.4085

Max Act: 1.3545. Min Act: -0.0001

Data Index: 412204 (C4 (Web Text))

Max Activating Token Index: 516

Text #13

Max Range: 1.4085. Min Range: -1.4085

Max Act: 1.3147. Min Act: -0.0001

Data Index: 734109 (C4 (Web Text))

Max Activating Token Index: 440

Text #14

Max Range: 1.4085. Min Range: -1.4085

Max Act: 1.3548. Min Act: -0.0001

Data Index: 1017751 (C4 (Web Text))

Max Activating Token Index: 882

Text #15

Max Range: 1.4085. Min Range: -1.4085

Max Act: 1.2348. Min Act: -0.0001

Data Index: 409927 (C4 (Web Text))

Max Activating Token Index: 399

Text #16

Max Range: 1.4085. Min Range: -1.4085

Max Act: 1.2835. Min Act: -0.0001

Data Index: 681056 (C4 (Web Text))

Max Activating Token Index: 842

Text #17

Max Range: 1.4085. Min Range: -1.4085

Max Act: 1.2122. Min Act: -0.0001

Data Index: 633163 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 1.4085. Min Range: -1.4085

Max Act: 1.1663. Min Act: -0.0001

Data Index: 1255512 (C4 (Web Text))

Max Activating Token Index: 187

Text #19

Max Range: 1.4085. Min Range: -1.4085

Max Act: 1.2391. Min Act: -0.0001

Data Index: 188952 (C4 (Web Text))

Max Activating Token Index: 595