Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 852 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.4506. Min Range: -3.4506

Max Act: 3.4506. Min Act: -0.1700

Data Index: 1413122 (Python Code)

Max Activating Token Index: 974

Text #1

Max Range: 3.4506. Min Range: -3.4506

Max Act: 3.3944. Min Act: -0.1700

Data Index: 1284501 (C4 (Web Text))

Max Activating Token Index: 891

Text #2

Max Range: 3.4506. Min Range: -3.4506

Max Act: 3.2827. Min Act: -0.1700

Data Index: 63920 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 3.4506. Min Range: -3.4506

Max Act: 3.2749. Min Act: -0.1700

Data Index: 1303512 (C4 (Web Text))

Max Activating Token Index: 73

Text #4

Max Range: 3.4506. Min Range: -3.4506

Max Act: 3.3027. Min Act: -0.1700

Data Index: 32825 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 3.4506. Min Range: -3.4506

Max Act: 3.3066. Min Act: -0.1700

Data Index: 238013 (C4 (Web Text))

Max Activating Token Index: 1012

Text #6

Max Range: 3.4506. Min Range: -3.4506

Max Act: 3.2904. Min Act: -0.1700

Data Index: 196155 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 3.4506. Min Range: -3.4506

Max Act: 3.2637. Min Act: -0.1700

Data Index: 155587 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 3.4506. Min Range: -3.4506

Max Act: 3.2602. Min Act: -0.1700

Data Index: 1072316 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 3.4506. Min Range: -3.4506

Max Act: 3.2453. Min Act: -0.1700

Data Index: 1090834 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 3.4506. Min Range: -3.4506

Max Act: 3.2456. Min Act: -0.1700

Data Index: 1176597 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 3.4506. Min Range: -3.4506

Max Act: 3.2658. Min Act: -0.1700

Data Index: 1256384 (C4 (Web Text))

Max Activating Token Index: 32

Text #12

Max Range: 3.4506. Min Range: -3.4506

Max Act: 3.2431. Min Act: -0.1700

Data Index: 348902 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 3.4506. Min Range: -3.4506

Max Act: 3.2401. Min Act: -0.1700

Data Index: 113906 (C4 (Web Text))

Max Activating Token Index: 572

Text #14

Max Range: 3.4506. Min Range: -3.4506

Max Act: 3.2703. Min Act: -0.1700

Data Index: 75448 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 3.4506. Min Range: -3.4506

Max Act: 3.2519. Min Act: -0.1700

Data Index: 927579 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 3.4506. Min Range: -3.4506

Max Act: 3.2565. Min Act: -0.1700

Data Index: 1171916 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 3.4506. Min Range: -3.4506

Max Act: 3.2203. Min Act: -0.1700

Data Index: 334762 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 3.4506. Min Range: -3.4506

Max Act: 3.2162. Min Act: -0.1700

Data Index: 198138 (C4 (Web Text))

Max Activating Token Index: 705

Text #19

Max Range: 3.4506. Min Range: -3.4506

Max Act: 3.2209. Min Act: -0.1700

Data Index: 437641 (C4 (Web Text))

Max Activating Token Index: 131