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

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

Neuron 3997 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: 0.4357. Min Range: -0.4357

Max Act: 0.4357. Min Act: -0.0001

Data Index: 407101 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.4357. Min Range: -0.4357

Max Act: 0.3768. Min Act: -0.0001

Data Index: 1313027 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 0.4357. Min Range: -0.4357

Max Act: 0.3147. Min Act: -0.0001

Data Index: 526812 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 0.4357. Min Range: -0.4357

Max Act: 0.3115. Min Act: -0.0001

Data Index: 82742 (C4 (Web Text))

Max Activating Token Index: 326

Text #4

Max Range: 0.4357. Min Range: -0.4357

Max Act: 0.3045. Min Act: -0.0001

Data Index: 1272639 (C4 (Web Text))

Max Activating Token Index: 632

Text #5

Max Range: 0.4357. Min Range: -0.4357

Max Act: 0.2946. Min Act: -0.0001

Data Index: 718032 (C4 (Web Text))

Max Activating Token Index: 221

Text #6

Max Range: 0.4357. Min Range: -0.4357

Max Act: 0.2885. Min Act: -0.0001

Data Index: 1629445 (Python Code)

Max Activating Token Index: 28

Text #7

Max Range: 0.4357. Min Range: -0.4357

Max Act: 0.2864. Min Act: -0.0001

Data Index: 80350 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 0.4357. Min Range: -0.4357

Max Act: 0.2847. Min Act: -0.0001

Data Index: 190587 (C4 (Web Text))

Max Activating Token Index: 971

Text #9

Max Range: 0.4357. Min Range: -0.4357

Max Act: 0.2815. Min Act: -0.0001

Data Index: 1057695 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 0.4357. Min Range: -0.4357

Max Act: 0.2802. Min Act: -0.0001

Data Index: 393057 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 0.4357. Min Range: -0.4357

Max Act: 0.2752. Min Act: -0.0001

Data Index: 639522 (C4 (Web Text))

Max Activating Token Index: 714

Text #12

Max Range: 0.4357. Min Range: -0.4357

Max Act: 0.2764. Min Act: -0.0001

Data Index: 459331 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 0.4357. Min Range: -0.4357

Max Act: 0.2792. Min Act: -0.0001

Data Index: 347880 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 0.4357. Min Range: -0.4357

Max Act: 0.2762. Min Act: -0.0001

Data Index: 195863 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 0.4357. Min Range: -0.4357

Max Act: 0.2706. Min Act: -0.0001

Data Index: 1218533 (C4 (Web Text))

Max Activating Token Index: 360

Text #16

Max Range: 0.4357. Min Range: -0.4357

Max Act: 0.2726. Min Act: -0.0001

Data Index: 235420 (C4 (Web Text))

Max Activating Token Index: 840

Text #17

Max Range: 0.4357. Min Range: -0.4357

Max Act: 0.2696. Min Act: -0.0001

Data Index: 808509 (C4 (Web Text))

Max Activating Token Index: 675

Text #18

Max Range: 0.4357. Min Range: -0.4357

Max Act: 0.2706. Min Act: -0.0001

Data Index: 775517 (C4 (Web Text))

Max Activating Token Index: 472

Text #19

Max Range: 0.4357. Min Range: -0.4357

Max Act: 0.2647. Min Act: -0.0001

Data Index: 1496362 (Python Code)

Max Activating Token Index: 391