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

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

Neuron 1076 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: 3.1517. Min Range: -3.1517

Max Act: 3.1517. Min Act: -0.1700

Data Index: 927836 (C4 (Web Text))

Max Activating Token Index: 278

Text #1

Max Range: 3.1517. Min Range: -3.1517

Max Act: 3.1110. Min Act: -0.1700

Data Index: 947824 (C4 (Web Text))

Max Activating Token Index: 501

Text #2

Max Range: 3.1517. Min Range: -3.1517

Max Act: 3.0909. Min Act: -0.1700

Data Index: 125273 (C4 (Web Text))

Max Activating Token Index: 324

Text #3

Max Range: 3.1517. Min Range: -3.1517

Max Act: 3.0822. Min Act: -0.1700

Data Index: 32487 (C4 (Web Text))

Max Activating Token Index: 579

Text #4

Max Range: 3.1517. Min Range: -3.1517

Max Act: 3.0443. Min Act: -0.1700

Data Index: 1515350 (Python Code)

Max Activating Token Index: 505

Text #5

Max Range: 3.1517. Min Range: -3.1517

Max Act: 3.0400. Min Act: -0.1700

Data Index: 362379 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 3.1517. Min Range: -3.1517

Max Act: 3.0484. Min Act: -0.1700

Data Index: 1159480 (C4 (Web Text))

Max Activating Token Index: 96

Text #7

Max Range: 3.1517. Min Range: -3.1517

Max Act: 3.0218. Min Act: -0.1700

Data Index: 1192655 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 3.1517. Min Range: -3.1517

Max Act: 3.0161. Min Act: -0.1699

Data Index: 1136376 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 3.1517. Min Range: -3.1517

Max Act: 3.0001. Min Act: -0.1700

Data Index: 1501659 (Python Code)

Max Activating Token Index: 107

Text #10

Max Range: 3.1517. Min Range: -3.1517

Max Act: 2.9990. Min Act: -0.1700

Data Index: 163735 (C4 (Web Text))

Max Activating Token Index: 601

Text #11

Max Range: 3.1517. Min Range: -3.1517

Max Act: 2.9970. Min Act: -0.1700

Data Index: 306926 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 3.1517. Min Range: -3.1517

Max Act: 2.9940. Min Act: -0.1700

Data Index: 610744 (C4 (Web Text))

Max Activating Token Index: 23

Text #13

Max Range: 3.1517. Min Range: -3.1517

Max Act: 2.9950. Min Act: -0.1700

Data Index: 1049335 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 3.1517. Min Range: -3.1517

Max Act: 2.9849. Min Act: -0.1699

Data Index: 992846 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 3.1517. Min Range: -3.1517

Max Act: 2.9778. Min Act: -0.1700

Data Index: 888461 (C4 (Web Text))

Max Activating Token Index: 739

Text #16

Max Range: 3.1517. Min Range: -3.1517

Max Act: 2.9803. Min Act: -0.1699

Data Index: 406980 (C4 (Web Text))

Max Activating Token Index: 941

Text #17

Max Range: 3.1517. Min Range: -3.1517

Max Act: 2.9798. Min Act: -0.1700

Data Index: 132388 (C4 (Web Text))

Max Activating Token Index: 366

Text #18

Max Range: 3.1517. Min Range: -3.1517

Max Act: 2.9642. Min Act: -0.1700

Data Index: 457259 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 3.1517. Min Range: -3.1517

Max Act: 2.9756. Min Act: -0.1699

Data Index: 230661 (C4 (Web Text))

Max Activating Token Index: 312