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

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

Neuron 3762 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: 0.2726. Min Range: -0.2726

Max Act: 0.2709. Min Act: -0.0003

Data Index: 589593 (C4 (Web Text))

Max Activating Token Index: 145

Text #1

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2726. Min Act: -0.0002

Data Index: 393246 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2672. Min Act: -0.0002

Data Index: 392308 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2522. Min Act: -0.0002

Data Index: 130341 (C4 (Web Text))

Max Activating Token Index: 153

Text #4

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2498. Min Act: -0.0002

Data Index: 566185 (C4 (Web Text))

Max Activating Token Index: 67

Text #5

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2434. Min Act: -0.0002

Data Index: 18426 (C4 (Web Text))

Max Activating Token Index: 252

Text #6

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2467. Min Act: -0.0002

Data Index: 1090202 (C4 (Web Text))

Max Activating Token Index: 520

Text #7

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2462. Min Act: -0.0002

Data Index: 752210 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2462. Min Act: -0.0002

Data Index: 176577 (C4 (Web Text))

Max Activating Token Index: 2

Text #9

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2462. Min Act: -0.0002

Data Index: 26070 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2450. Min Act: -0.0002

Data Index: 95979 (C4 (Web Text))

Max Activating Token Index: 857

Text #11

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2415. Min Act: -0.0002

Data Index: 204152 (C4 (Web Text))

Max Activating Token Index: 545

Text #12

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2292. Min Act: -0.0002

Data Index: 9700 (C4 (Web Text))

Max Activating Token Index: 684

Text #13

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2390. Min Act: -0.0002

Data Index: 250781 (C4 (Web Text))

Max Activating Token Index: 876

Text #14

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2344. Min Act: -0.0002

Data Index: 884667 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2344. Min Act: -0.0002

Data Index: 1050413 (C4 (Web Text))

Max Activating Token Index: 4

Text #16

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2288. Min Act: -0.0002

Data Index: 778224 (C4 (Web Text))

Max Activating Token Index: 76

Text #17

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2344. Min Act: -0.0002

Data Index: 1020066 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2311. Min Act: -0.0002

Data Index: 104050 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 0.2726. Min Range: -0.2726

Max Act: 0.2193. Min Act: -0.0002

Data Index: 125736 (C4 (Web Text))

Max Activating Token Index: 601