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

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

Neuron 865 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: 3.6755. Min Range: -3.6755

Max Act: 3.6755. Min Act: -0.1700

Data Index: 336122 (C4 (Web Text))

Max Activating Token Index: 525

Text #1

Max Range: 3.6755. Min Range: -3.6755

Max Act: 3.6084. Min Act: -0.1700

Data Index: 376997 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 3.6755. Min Range: -3.6755

Max Act: 3.5884. Min Act: -0.1700

Data Index: 1185466 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 3.6755. Min Range: -3.6755

Max Act: 3.5845. Min Act: -0.1700

Data Index: 1130353 (C4 (Web Text))

Max Activating Token Index: 733

Text #4

Max Range: 3.6755. Min Range: -3.6755

Max Act: 3.5947. Min Act: -0.1700

Data Index: 173000 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 3.6755. Min Range: -3.6755

Max Act: 3.5869. Min Act: -0.1700

Data Index: 1338522 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 3.6755. Min Range: -3.6755

Max Act: 3.5616. Min Act: -0.1700

Data Index: 804322 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 3.6755. Min Range: -3.6755

Max Act: 3.5315. Min Act: -0.1700

Data Index: 1132493 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 3.6755. Min Range: -3.6755

Max Act: 3.5198. Min Act: -0.1700

Data Index: 920680 (C4 (Web Text))

Max Activating Token Index: 586

Text #9

Max Range: 3.6755. Min Range: -3.6755

Max Act: 3.5208. Min Act: -0.1700

Data Index: 1030217 (C4 (Web Text))

Max Activating Token Index: 415

Text #10

Max Range: 3.6755. Min Range: -3.6755

Max Act: 3.4890. Min Act: -0.1700

Data Index: 655065 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 3.6755. Min Range: -3.6755

Max Act: 3.4712. Min Act: -0.1700

Data Index: 737155 (C4 (Web Text))

Max Activating Token Index: 524

Text #12

Max Range: 3.6755. Min Range: -3.6755

Max Act: 3.4596. Min Act: -0.1700

Data Index: 700094 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 3.6755. Min Range: -3.6755

Max Act: 3.4572. Min Act: -0.1700

Data Index: 1041852 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 3.6755. Min Range: -3.6755

Max Act: 3.4578. Min Act: -0.1700

Data Index: 10789 (C4 (Web Text))

Max Activating Token Index: 492

Text #15

Max Range: 3.6755. Min Range: -3.6755

Max Act: 3.4742. Min Act: -0.1700

Data Index: 314942 (C4 (Web Text))

Max Activating Token Index: 364

Text #16

Max Range: 3.6755. Min Range: -3.6755

Max Act: 3.4529. Min Act: -0.1700

Data Index: 288190 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 3.6755. Min Range: -3.6755

Max Act: 3.4479. Min Act: -0.1700

Data Index: 102432 (C4 (Web Text))

Max Activating Token Index: 500

Text #18

Max Range: 3.6755. Min Range: -3.6755

Max Act: 3.4521. Min Act: -0.1700

Data Index: 208314 (C4 (Web Text))

Max Activating Token Index: 742

Text #19

Max Range: 3.6755. Min Range: -3.6755

Max Act: 3.4595. Min Act: -0.1700

Data Index: 1150040 (C4 (Web Text))

Max Activating Token Index: 963