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

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

Neuron 620 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: 3.2381. Min Range: -3.2381

Max Act: 3.2381. Min Act: -0.1700

Data Index: 586182 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 3.2381. Min Range: -3.2381

Max Act: 3.2374. Min Act: -0.1700

Data Index: 603386 (C4 (Web Text))

Max Activating Token Index: 367

Text #2

Max Range: 3.2381. Min Range: -3.2381

Max Act: 3.1636. Min Act: -0.1700

Data Index: 180548 (C4 (Web Text))

Max Activating Token Index: 341

Text #3

Max Range: 3.2381. Min Range: -3.2381

Max Act: 3.1594. Min Act: -0.1700

Data Index: 359044 (C4 (Web Text))

Max Activating Token Index: 302

Text #4

Max Range: 3.2381. Min Range: -3.2381

Max Act: 3.1537. Min Act: -0.1700

Data Index: 489334 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 3.2381. Min Range: -3.2381

Max Act: 3.1359. Min Act: -0.1700

Data Index: 1400724 (Python Code)

Max Activating Token Index: 375

Text #6

Max Range: 3.2381. Min Range: -3.2381

Max Act: 3.1244. Min Act: -0.1700

Data Index: 1560355 (Python Code)

Max Activating Token Index: 815

Text #7

Max Range: 3.2381. Min Range: -3.2381

Max Act: 3.1145. Min Act: -0.1700

Data Index: 443019 (C4 (Web Text))

Max Activating Token Index: 972

Text #8

Max Range: 3.2381. Min Range: -3.2381

Max Act: 3.1265. Min Act: -0.1700

Data Index: 1644190 (Python Code)

Max Activating Token Index: 412

Text #9

Max Range: 3.2381. Min Range: -3.2381

Max Act: 3.1183. Min Act: -0.1700

Data Index: 1318934 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 3.2381. Min Range: -3.2381

Max Act: 3.1010. Min Act: -0.1700

Data Index: 1292784 (C4 (Web Text))

Max Activating Token Index: 282

Text #11

Max Range: 3.2381. Min Range: -3.2381

Max Act: 3.0980. Min Act: -0.1700

Data Index: 342244 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 3.2381. Min Range: -3.2381

Max Act: 3.0971. Min Act: -0.1700

Data Index: 174959 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 3.2381. Min Range: -3.2381

Max Act: 3.0769. Min Act: -0.1700

Data Index: 163730 (C4 (Web Text))

Max Activating Token Index: 211

Text #14

Max Range: 3.2381. Min Range: -3.2381

Max Act: 3.0916. Min Act: -0.1700

Data Index: 406649 (C4 (Web Text))

Max Activating Token Index: 11

Text #15

Max Range: 3.2381. Min Range: -3.2381

Max Act: 3.0885. Min Act: -0.1700

Data Index: 626197 (C4 (Web Text))

Max Activating Token Index: 964

Text #16

Max Range: 3.2381. Min Range: -3.2381

Max Act: 3.0709. Min Act: -0.1700

Data Index: 1035351 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 3.2381. Min Range: -3.2381

Max Act: 3.0819. Min Act: -0.1700

Data Index: 646260 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 3.2381. Min Range: -3.2381

Max Act: 3.0602. Min Act: -0.1700

Data Index: 1445049 (Python Code)

Max Activating Token Index: 592

Text #19

Max Range: 3.2381. Min Range: -3.2381

Max Act: 3.0519. Min Act: -0.1700

Data Index: 218243 (C4 (Web Text))

Max Activating Token Index: 502