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

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

Neuron 1633 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: 5.6762. Min Range: -5.6762

Max Act: 5.6762. Min Act: -0.1700

Data Index: 404168 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 5.6762. Min Range: -5.6762

Max Act: 5.6560. Min Act: -0.1700

Data Index: 416462 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 5.6762. Min Range: -5.6762

Max Act: 5.5884. Min Act: -0.1700

Data Index: 540232 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 5.6762. Min Range: -5.6762

Max Act: 5.4241. Min Act: -0.1700

Data Index: 444862 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 5.6762. Min Range: -5.6762

Max Act: 5.1982. Min Act: -0.1700

Data Index: 1153435 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 5.6762. Min Range: -5.6762

Max Act: 5.1476. Min Act: -0.1700

Data Index: 992765 (C4 (Web Text))

Max Activating Token Index: 894

Text #6

Max Range: 5.6762. Min Range: -5.6762

Max Act: 5.1244. Min Act: -0.1700

Data Index: 91152 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 5.6762. Min Range: -5.6762

Max Act: 5.1096. Min Act: -0.1700

Data Index: 362097 (C4 (Web Text))

Max Activating Token Index: 676

Text #8

Max Range: 5.6762. Min Range: -5.6762

Max Act: 5.0776. Min Act: -0.1700

Data Index: 914130 (C4 (Web Text))

Max Activating Token Index: 873

Text #9

Max Range: 5.6762. Min Range: -5.6762

Max Act: 5.0841. Min Act: -0.1700

Data Index: 523453 (C4 (Web Text))

Max Activating Token Index: 957

Text #10

Max Range: 5.6762. Min Range: -5.6762

Max Act: 5.0513. Min Act: -0.1700

Data Index: 861124 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 5.6762. Min Range: -5.6762

Max Act: 5.0432. Min Act: -0.1700

Data Index: 682444 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 5.6762. Min Range: -5.6762

Max Act: 5.0195. Min Act: -0.1700

Data Index: 342809 (C4 (Web Text))

Max Activating Token Index: 172

Text #13

Max Range: 5.6762. Min Range: -5.6762

Max Act: 5.0006. Min Act: -0.1700

Data Index: 493039 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 5.6762. Min Range: -5.6762

Max Act: 5.0347. Min Act: -0.1700

Data Index: 1269503 (C4 (Web Text))

Max Activating Token Index: 955

Text #15

Max Range: 5.6762. Min Range: -5.6762

Max Act: 4.9219. Min Act: -0.1700

Data Index: 141598 (C4 (Web Text))

Max Activating Token Index: 408

Text #16

Max Range: 5.6762. Min Range: -5.6762

Max Act: 4.9311. Min Act: -0.1700

Data Index: 28975 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 5.6762. Min Range: -5.6762

Max Act: 4.9532. Min Act: -0.1700

Data Index: 682058 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 5.6762. Min Range: -5.6762

Max Act: 4.9593. Min Act: -0.1700

Data Index: 694011 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 5.6762. Min Range: -5.6762

Max Act: 4.9357. Min Act: -0.1700

Data Index: 547956 (C4 (Web Text))

Max Activating Token Index: 721