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

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

Neuron 1360 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: 4.1275. Min Range: -4.1275

Max Act: 4.1275. Min Act: -0.1700

Data Index: 1356621 (C4 (Web Text))

Max Activating Token Index: 721

Text #1

Max Range: 4.1275. Min Range: -4.1275

Max Act: 4.0349. Min Act: -0.1700

Data Index: 1176151 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 4.1275. Min Range: -4.1275

Max Act: 3.9825. Min Act: -0.1700

Data Index: 661029 (C4 (Web Text))

Max Activating Token Index: 471

Text #3

Max Range: 4.1275. Min Range: -4.1275

Max Act: 3.9996. Min Act: -0.1700

Data Index: 734470 (C4 (Web Text))

Max Activating Token Index: 534

Text #4

Max Range: 4.1275. Min Range: -4.1275

Max Act: 3.9357. Min Act: -0.1700

Data Index: 765485 (C4 (Web Text))

Max Activating Token Index: 553

Text #5

Max Range: 4.1275. Min Range: -4.1275

Max Act: 3.8473. Min Act: -0.1700

Data Index: 666848 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 4.1275. Min Range: -4.1275

Max Act: 3.8587. Min Act: -0.1700

Data Index: 131478 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 4.1275. Min Range: -4.1275

Max Act: 3.8309. Min Act: -0.1699

Data Index: 1284203 (C4 (Web Text))

Max Activating Token Index: 555

Text #8

Max Range: 4.1275. Min Range: -4.1275

Max Act: 3.8467. Min Act: -0.1700

Data Index: 1209511 (C4 (Web Text))

Max Activating Token Index: 349

Text #9

Max Range: 4.1275. Min Range: -4.1275

Max Act: 3.7844. Min Act: -0.1697

Data Index: 366360 (C4 (Web Text))

Max Activating Token Index: 511

Text #10

Max Range: 4.1275. Min Range: -4.1275

Max Act: 3.7539. Min Act: -0.1700

Data Index: 1461535 (Python Code)

Max Activating Token Index: 181

Text #11

Max Range: 4.1275. Min Range: -4.1275

Max Act: 3.7251. Min Act: -0.1698

Data Index: 239733 (C4 (Web Text))

Max Activating Token Index: 1011

Text #12

Max Range: 4.1275. Min Range: -4.1275

Max Act: 3.7384. Min Act: -0.1700

Data Index: 1335813 (C4 (Web Text))

Max Activating Token Index: 450

Text #13

Max Range: 4.1275. Min Range: -4.1275

Max Act: 3.7514. Min Act: -0.1700

Data Index: 194286 (C4 (Web Text))

Max Activating Token Index: 539

Text #14

Max Range: 4.1275. Min Range: -4.1275

Max Act: 3.7419. Min Act: -0.1700

Data Index: 1203248 (C4 (Web Text))

Max Activating Token Index: 636

Text #15

Max Range: 4.1275. Min Range: -4.1275

Max Act: 3.7019. Min Act: -0.1699

Data Index: 966459 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 4.1275. Min Range: -4.1275

Max Act: 3.6748. Min Act: -0.1700

Data Index: 892908 (C4 (Web Text))

Max Activating Token Index: 689

Text #17

Max Range: 4.1275. Min Range: -4.1275

Max Act: 3.6725. Min Act: -0.1699

Data Index: 359299 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 4.1275. Min Range: -4.1275

Max Act: 3.6800. Min Act: -0.1700

Data Index: 985151 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 4.1275. Min Range: -4.1275

Max Act: 3.6491. Min Act: -0.1700

Data Index: 522616 (C4 (Web Text))

Max Activating Token Index: 654