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

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

Neuron 403 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: 3.8426. Min Range: -3.8426

Max Act: 3.8426. Min Act: -0.1699

Data Index: 215676 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 3.8426. Min Range: -3.8426

Max Act: 3.7873. Min Act: -0.1700

Data Index: 1014021 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 3.8426. Min Range: -3.8426

Max Act: 3.7841. Min Act: -0.1699

Data Index: 979708 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 3.8426. Min Range: -3.8426

Max Act: 3.7661. Min Act: -0.1700

Data Index: 552358 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 3.8426. Min Range: -3.8426

Max Act: 3.7491. Min Act: -0.1700

Data Index: 980407 (C4 (Web Text))

Max Activating Token Index: 798

Text #5

Max Range: 3.8426. Min Range: -3.8426

Max Act: 3.7160. Min Act: -0.1699

Data Index: 1637988 (Python Code)

Max Activating Token Index: 968

Text #6

Max Range: 3.8426. Min Range: -3.8426

Max Act: 3.7522. Min Act: -0.1700

Data Index: 1180480 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 3.8426. Min Range: -3.8426

Max Act: 3.7197. Min Act: -0.1698

Data Index: 736736 (C4 (Web Text))

Max Activating Token Index: 633

Text #8

Max Range: 3.8426. Min Range: -3.8426

Max Act: 3.7058. Min Act: -0.1648

Data Index: 1280471 (C4 (Web Text))

Max Activating Token Index: 441

Text #9

Max Range: 3.8426. Min Range: -3.8426

Max Act: 3.6950. Min Act: -0.1683

Data Index: 1611779 (Python Code)

Max Activating Token Index: 912

Text #10

Max Range: 3.8426. Min Range: -3.8426

Max Act: 3.6192. Min Act: -0.1700

Data Index: 1399897 (Python Code)

Max Activating Token Index: 969

Text #11

Max Range: 3.8426. Min Range: -3.8426

Max Act: 3.6409. Min Act: -0.1696

Data Index: 1540210 (Python Code)

Max Activating Token Index: 842

Text #12

Max Range: 3.8426. Min Range: -3.8426

Max Act: 3.6376. Min Act: -0.1700

Data Index: 599102 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 3.8426. Min Range: -3.8426

Max Act: 3.6551. Min Act: -0.1699

Data Index: 23067 (C4 (Web Text))

Max Activating Token Index: 899

Text #14

Max Range: 3.8426. Min Range: -3.8426

Max Act: 3.6223. Min Act: -0.1699

Data Index: 989272 (C4 (Web Text))

Max Activating Token Index: 756

Text #15

Max Range: 3.8426. Min Range: -3.8426

Max Act: 3.6436. Min Act: -0.1700

Data Index: 501945 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 3.8426. Min Range: -3.8426

Max Act: 3.6203. Min Act: -0.1700

Data Index: 1323520 (C4 (Web Text))

Max Activating Token Index: 610

Text #17

Max Range: 3.8426. Min Range: -3.8426

Max Act: 3.6412. Min Act: -0.1700

Data Index: 883093 (C4 (Web Text))

Max Activating Token Index: 786

Text #18

Max Range: 3.8426. Min Range: -3.8426

Max Act: 3.5959. Min Act: -0.1687

Data Index: 39023 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 3.8426. Min Range: -3.8426

Max Act: 3.6027. Min Act: -0.1700

Data Index: 65859 (C4 (Web Text))

Max Activating Token Index: 911