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

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

Neuron 117 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: 3.4005. Min Range: -3.4005

Max Act: 3.4005. Min Act: -0.1700

Data Index: 2772 (C4 (Web Text))

Max Activating Token Index: 369

Text #1

Max Range: 3.4005. Min Range: -3.4005

Max Act: 3.2172. Min Act: -0.1700

Data Index: 1406480 (Python Code)

Max Activating Token Index: 982

Text #2

Max Range: 3.4005. Min Range: -3.4005

Max Act: 3.1703. Min Act: -0.1700

Data Index: 1088700 (C4 (Web Text))

Max Activating Token Index: 816

Text #3

Max Range: 3.4005. Min Range: -3.4005

Max Act: 3.1273. Min Act: -0.1700

Data Index: 447831 (C4 (Web Text))

Max Activating Token Index: 557

Text #4

Max Range: 3.4005. Min Range: -3.4005

Max Act: 3.1004. Min Act: -0.1700

Data Index: 44181 (C4 (Web Text))

Max Activating Token Index: 792

Text #5

Max Range: 3.4005. Min Range: -3.4005

Max Act: 3.0484. Min Act: -0.1700

Data Index: 806881 (C4 (Web Text))

Max Activating Token Index: 925

Text #6

Max Range: 3.4005. Min Range: -3.4005

Max Act: 3.0534. Min Act: -0.1700

Data Index: 1613806 (Python Code)

Max Activating Token Index: 26

Text #7

Max Range: 3.4005. Min Range: -3.4005

Max Act: 3.0304. Min Act: -0.1700

Data Index: 49561 (C4 (Web Text))

Max Activating Token Index: 713

Text #8

Max Range: 3.4005. Min Range: -3.4005

Max Act: 3.0496. Min Act: -0.1700

Data Index: 1053004 (C4 (Web Text))

Max Activating Token Index: 416

Text #9

Max Range: 3.4005. Min Range: -3.4005

Max Act: 2.9996. Min Act: -0.1700

Data Index: 150469 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 3.4005. Min Range: -3.4005

Max Act: 2.9761. Min Act: -0.1700

Data Index: 268236 (C4 (Web Text))

Max Activating Token Index: 75

Text #11

Max Range: 3.4005. Min Range: -3.4005

Max Act: 2.9864. Min Act: -0.1700

Data Index: 406164 (C4 (Web Text))

Max Activating Token Index: 581

Text #12

Max Range: 3.4005. Min Range: -3.4005

Max Act: 3.0054. Min Act: -0.1700

Data Index: 1353133 (C4 (Web Text))

Max Activating Token Index: 201

Text #13

Max Range: 3.4005. Min Range: -3.4005

Max Act: 2.9809. Min Act: -0.1700

Data Index: 583027 (C4 (Web Text))

Max Activating Token Index: 265

Text #14

Max Range: 3.4005. Min Range: -3.4005

Max Act: 2.9857. Min Act: -0.1700

Data Index: 563982 (C4 (Web Text))

Max Activating Token Index: 412

Text #15

Max Range: 3.4005. Min Range: -3.4005

Max Act: 2.9385. Min Act: -0.1700

Data Index: 1597118 (Python Code)

Max Activating Token Index: 467

Text #16

Max Range: 3.4005. Min Range: -3.4005

Max Act: 2.9535. Min Act: -0.1700

Data Index: 1506721 (Python Code)

Max Activating Token Index: 348

Text #17

Max Range: 3.4005. Min Range: -3.4005

Max Act: 2.9192. Min Act: -0.1700

Data Index: 300347 (C4 (Web Text))

Max Activating Token Index: 809

Text #18

Max Range: 3.4005. Min Range: -3.4005

Max Act: 2.9608. Min Act: -0.1700

Data Index: 1018453 (C4 (Web Text))

Max Activating Token Index: 300

Text #19

Max Range: 3.4005. Min Range: -3.4005

Max Act: 2.9674. Min Act: -0.1700

Data Index: 353814 (C4 (Web Text))

Max Activating Token Index: 614