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

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

Neuron 1128 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: 3.5682. Min Range: -3.5682

Max Act: 3.5682. Min Act: -0.1700

Data Index: 486963 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 3.5682. Min Range: -3.5682

Max Act: 3.4389. Min Act: -0.1700

Data Index: 55530 (C4 (Web Text))

Max Activating Token Index: 506

Text #2

Max Range: 3.5682. Min Range: -3.5682

Max Act: 3.4458. Min Act: -0.1700

Data Index: 1146689 (C4 (Web Text))

Max Activating Token Index: 496

Text #3

Max Range: 3.5682. Min Range: -3.5682

Max Act: 3.4211. Min Act: -0.1700

Data Index: 398803 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 3.5682. Min Range: -3.5682

Max Act: 3.3919. Min Act: -0.1700

Data Index: 412310 (C4 (Web Text))

Max Activating Token Index: 297

Text #5

Max Range: 3.5682. Min Range: -3.5682

Max Act: 3.3637. Min Act: -0.1700

Data Index: 340521 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 3.5682. Min Range: -3.5682

Max Act: 3.3456. Min Act: -0.1700

Data Index: 838069 (C4 (Web Text))

Max Activating Token Index: 351

Text #7

Max Range: 3.5682. Min Range: -3.5682

Max Act: 3.3480. Min Act: -0.1700

Data Index: 541610 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 3.5682. Min Range: -3.5682

Max Act: 3.3377. Min Act: -0.1700

Data Index: 1189491 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 3.5682. Min Range: -3.5682

Max Act: 3.3249. Min Act: -0.1700

Data Index: 273205 (C4 (Web Text))

Max Activating Token Index: 148

Text #10

Max Range: 3.5682. Min Range: -3.5682

Max Act: 3.3115. Min Act: -0.1700

Data Index: 310569 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 3.5682. Min Range: -3.5682

Max Act: 3.3012. Min Act: -0.1700

Data Index: 438828 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 3.5682. Min Range: -3.5682

Max Act: 3.3032. Min Act: -0.1700

Data Index: 984707 (C4 (Web Text))

Max Activating Token Index: 349

Text #13

Max Range: 3.5682. Min Range: -3.5682

Max Act: 3.3001. Min Act: -0.1700

Data Index: 643321 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 3.5682. Min Range: -3.5682

Max Act: 3.2974. Min Act: -0.1700

Data Index: 1063590 (C4 (Web Text))

Max Activating Token Index: 312

Text #15

Max Range: 3.5682. Min Range: -3.5682

Max Act: 3.2993. Min Act: -0.1700

Data Index: 8428 (C4 (Web Text))

Max Activating Token Index: 843

Text #16

Max Range: 3.5682. Min Range: -3.5682

Max Act: 3.2910. Min Act: -0.1700

Data Index: 1045951 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 3.5682. Min Range: -3.5682

Max Act: 3.2931. Min Act: -0.1700

Data Index: 89165 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 3.5682. Min Range: -3.5682

Max Act: 3.2661. Min Act: -0.1700

Data Index: 38198 (C4 (Web Text))

Max Activating Token Index: 936

Text #19

Max Range: 3.5682. Min Range: -3.5682

Max Act: 3.3231. Min Act: -0.1700

Data Index: 786852 (C4 (Web Text))

Max Activating Token Index: 1010