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

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

Neuron 645 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: 3.6737. Min Range: -3.6737

Max Act: 3.6737. Min Act: -0.1700

Data Index: 766364 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.5078. Min Act: -0.1700

Data Index: 1356128 (C4 (Web Text))

Max Activating Token Index: 234

Text #2

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.4357. Min Act: -0.1700

Data Index: 1176292 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.4051. Min Act: -0.1700

Data Index: 46188 (C4 (Web Text))

Max Activating Token Index: 611

Text #4

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.4270. Min Act: -0.1700

Data Index: 259498 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.4289. Min Act: -0.1699

Data Index: 182226 (C4 (Web Text))

Max Activating Token Index: 553

Text #6

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.3943. Min Act: -0.1699

Data Index: 695109 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.3861. Min Act: -0.1700

Data Index: 296550 (C4 (Web Text))

Max Activating Token Index: 869

Text #8

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.3500. Min Act: -0.1700

Data Index: 660086 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.3569. Min Act: -0.1700

Data Index: 469406 (C4 (Web Text))

Max Activating Token Index: 716

Text #10

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.3365. Min Act: -0.1700

Data Index: 305482 (C4 (Web Text))

Max Activating Token Index: 433

Text #11

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.3213. Min Act: -0.1700

Data Index: 612799 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.3134. Min Act: -0.1700

Data Index: 849911 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.3324. Min Act: -0.1700

Data Index: 131017 (C4 (Web Text))

Max Activating Token Index: 507

Text #14

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.2781. Min Act: -0.1700

Data Index: 840954 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.3018. Min Act: -0.1699

Data Index: 930412 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.2947. Min Act: -0.1700

Data Index: 1288637 (C4 (Web Text))

Max Activating Token Index: 834

Text #17

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.2824. Min Act: -0.1700

Data Index: 1134018 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.2876. Min Act: -0.1700

Data Index: 1124800 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.3044. Min Act: -0.1700

Data Index: 1077951 (C4 (Web Text))

Max Activating Token Index: 176