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

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

Neuron 394 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: 3.7442. Min Range: -3.7442

Max Act: 3.7442. Min Act: -0.1700

Data Index: 999934 (C4 (Web Text))

Max Activating Token Index: 917

Text #1

Max Range: 3.7442. Min Range: -3.7442

Max Act: 3.7255. Min Act: -0.1699

Data Index: 325507 (C4 (Web Text))

Max Activating Token Index: 762

Text #2

Max Range: 3.7442. Min Range: -3.7442

Max Act: 3.6755. Min Act: -0.1386

Data Index: 829719 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 3.7442. Min Range: -3.7442

Max Act: 3.6713. Min Act: -0.1700

Data Index: 47572 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 3.7442. Min Range: -3.7442

Max Act: 3.6747. Min Act: -0.1700

Data Index: 56948 (C4 (Web Text))

Max Activating Token Index: 442

Text #5

Max Range: 3.7442. Min Range: -3.7442

Max Act: 3.6567. Min Act: -0.1690

Data Index: 878864 (C4 (Web Text))

Max Activating Token Index: 835

Text #6

Max Range: 3.7442. Min Range: -3.7442

Max Act: 3.6419. Min Act: -0.1700

Data Index: 646540 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 3.7442. Min Range: -3.7442

Max Act: 3.6409. Min Act: -0.1678

Data Index: 1041723 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 3.7442. Min Range: -3.7442

Max Act: 3.6571. Min Act: -0.1700

Data Index: 728210 (C4 (Web Text))

Max Activating Token Index: 335

Text #9

Max Range: 3.7442. Min Range: -3.7442

Max Act: 3.6586. Min Act: -0.1700

Data Index: 305650 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 3.7442. Min Range: -3.7442

Max Act: 3.6587. Min Act: -0.1700

Data Index: 38132 (C4 (Web Text))

Max Activating Token Index: 895

Text #11

Max Range: 3.7442. Min Range: -3.7442

Max Act: 3.6404. Min Act: -0.1386

Data Index: 124740 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 3.7442. Min Range: -3.7442

Max Act: 3.6222. Min Act: -0.1698

Data Index: 315777 (C4 (Web Text))

Max Activating Token Index: 521

Text #13

Max Range: 3.7442. Min Range: -3.7442

Max Act: 3.6059. Min Act: -0.1700

Data Index: 659567 (C4 (Web Text))

Max Activating Token Index: 655

Text #14

Max Range: 3.7442. Min Range: -3.7442

Max Act: 3.6234. Min Act: -0.1425

Data Index: 938061 (C4 (Web Text))

Max Activating Token Index: 409

Text #15

Max Range: 3.7442. Min Range: -3.7442

Max Act: 3.6255. Min Act: -0.1698

Data Index: 1238418 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 3.7442. Min Range: -3.7442

Max Act: 3.6168. Min Act: -0.1700

Data Index: 1114056 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 3.7442. Min Range: -3.7442

Max Act: 3.6140. Min Act: -0.1700

Data Index: 1109401 (C4 (Web Text))

Max Activating Token Index: 1006

Text #18

Max Range: 3.7442. Min Range: -3.7442

Max Act: 3.6126. Min Act: -0.1700

Data Index: 528817 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 3.7442. Min Range: -3.7442

Max Act: 3.5712. Min Act: -0.1700

Data Index: 17918 (C4 (Web Text))

Max Activating Token Index: 1006