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

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

Neuron 1344 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: 3.6297. Min Range: -3.6297

Max Act: 3.6297. Min Act: -0.1700

Data Index: 335750 (C4 (Web Text))

Max Activating Token Index: 509

Text #1

Max Range: 3.6297. Min Range: -3.6297

Max Act: 3.5086. Min Act: -0.1700

Data Index: 1268264 (C4 (Web Text))

Max Activating Token Index: 226

Text #2

Max Range: 3.6297. Min Range: -3.6297

Max Act: 3.4859. Min Act: -0.1700

Data Index: 722391 (C4 (Web Text))

Max Activating Token Index: 357

Text #3

Max Range: 3.6297. Min Range: -3.6297

Max Act: 3.4894. Min Act: -0.1700

Data Index: 1295888 (C4 (Web Text))

Max Activating Token Index: 765

Text #4

Max Range: 3.6297. Min Range: -3.6297

Max Act: 3.4591. Min Act: -0.1700

Data Index: 1114817 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 3.6297. Min Range: -3.6297

Max Act: 3.4477. Min Act: -0.1700

Data Index: 933864 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 3.6297. Min Range: -3.6297

Max Act: 3.4528. Min Act: -0.1699

Data Index: 917646 (C4 (Web Text))

Max Activating Token Index: 596

Text #7

Max Range: 3.6297. Min Range: -3.6297

Max Act: 3.4373. Min Act: -0.1700

Data Index: 410539 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 3.6297. Min Range: -3.6297

Max Act: 3.4333. Min Act: -0.1700

Data Index: 457651 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 3.6297. Min Range: -3.6297

Max Act: 3.4339. Min Act: -0.1700

Data Index: 208712 (C4 (Web Text))

Max Activating Token Index: 238

Text #10

Max Range: 3.6297. Min Range: -3.6297

Max Act: 3.4219. Min Act: -0.1700

Data Index: 1247199 (C4 (Web Text))

Max Activating Token Index: 585

Text #11

Max Range: 3.6297. Min Range: -3.6297

Max Act: 3.3984. Min Act: -0.1700

Data Index: 99711 (C4 (Web Text))

Max Activating Token Index: 7

Text #12

Max Range: 3.6297. Min Range: -3.6297

Max Act: 3.4063. Min Act: -0.1700

Data Index: 884246 (C4 (Web Text))

Max Activating Token Index: 608

Text #13

Max Range: 3.6297. Min Range: -3.6297

Max Act: 3.4022. Min Act: -0.1700

Data Index: 866787 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 3.6297. Min Range: -3.6297

Max Act: 3.3960. Min Act: -0.1700

Data Index: 99789 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 3.6297. Min Range: -3.6297

Max Act: 3.3884. Min Act: -0.1700

Data Index: 831818 (C4 (Web Text))

Max Activating Token Index: 711

Text #16

Max Range: 3.6297. Min Range: -3.6297

Max Act: 3.3883. Min Act: -0.1700

Data Index: 495939 (C4 (Web Text))

Max Activating Token Index: 817

Text #17

Max Range: 3.6297. Min Range: -3.6297

Max Act: 3.3860. Min Act: -0.1700

Data Index: 5159 (C4 (Web Text))

Max Activating Token Index: 652

Text #18

Max Range: 3.6297. Min Range: -3.6297

Max Act: 3.3852. Min Act: -0.1700

Data Index: 256035 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 3.6297. Min Range: -3.6297

Max Act: 3.3761. Min Act: -0.1700

Data Index: 256943 (C4 (Web Text))

Max Activating Token Index: 116