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

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

Neuron 2016 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: 3.7572. Min Range: -3.7572

Max Act: 3.7572. Min Act: -0.1700

Data Index: 371130 (C4 (Web Text))

Max Activating Token Index: 800

Text #1

Max Range: 3.7572. Min Range: -3.7572

Max Act: 3.7438. Min Act: -0.1700

Data Index: 1362011 (Python Code)

Max Activating Token Index: 722

Text #2

Max Range: 3.7572. Min Range: -3.7572

Max Act: 3.7274. Min Act: -0.1700

Data Index: 385020 (C4 (Web Text))

Max Activating Token Index: 972

Text #3

Max Range: 3.7572. Min Range: -3.7572

Max Act: 3.7212. Min Act: -0.1700

Data Index: 641351 (C4 (Web Text))

Max Activating Token Index: 817

Text #4

Max Range: 3.7572. Min Range: -3.7572

Max Act: 3.6956. Min Act: -0.1700

Data Index: 628132 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 3.7572. Min Range: -3.7572

Max Act: 3.6920. Min Act: -0.1700

Data Index: 1253971 (C4 (Web Text))

Max Activating Token Index: 801

Text #6

Max Range: 3.7572. Min Range: -3.7572

Max Act: 3.6817. Min Act: -0.1700

Data Index: 564244 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 3.7572. Min Range: -3.7572

Max Act: 3.6645. Min Act: -0.1700

Data Index: 400085 (C4 (Web Text))

Max Activating Token Index: 609

Text #8

Max Range: 3.7572. Min Range: -3.7572

Max Act: 3.6689. Min Act: -0.1700

Data Index: 535986 (C4 (Web Text))

Max Activating Token Index: 799

Text #9

Max Range: 3.7572. Min Range: -3.7572

Max Act: 3.6340. Min Act: -0.1700

Data Index: 1462302 (Python Code)

Max Activating Token Index: 265

Text #10

Max Range: 3.7572. Min Range: -3.7572

Max Act: 3.6321. Min Act: -0.1700

Data Index: 1136030 (C4 (Web Text))

Max Activating Token Index: 618

Text #11

Max Range: 3.7572. Min Range: -3.7572

Max Act: 3.6290. Min Act: -0.1700

Data Index: 513739 (C4 (Web Text))

Max Activating Token Index: 175

Text #12

Max Range: 3.7572. Min Range: -3.7572

Max Act: 3.6181. Min Act: -0.1700

Data Index: 312715 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 3.7572. Min Range: -3.7572

Max Act: 3.6312. Min Act: -0.1700

Data Index: 191075 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 3.7572. Min Range: -3.7572

Max Act: 3.6058. Min Act: -0.1700

Data Index: 406317 (C4 (Web Text))

Max Activating Token Index: 38

Text #15

Max Range: 3.7572. Min Range: -3.7572

Max Act: 3.5987. Min Act: -0.1700

Data Index: 1229563 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 3.7572. Min Range: -3.7572

Max Act: 3.5972. Min Act: -0.1700

Data Index: 1408251 (Python Code)

Max Activating Token Index: 635

Text #17

Max Range: 3.7572. Min Range: -3.7572

Max Act: 3.5857. Min Act: -0.1700

Data Index: 1585991 (Python Code)

Max Activating Token Index: 951

Text #18

Max Range: 3.7572. Min Range: -3.7572

Max Act: 3.5798. Min Act: -0.1700

Data Index: 1635465 (Python Code)

Max Activating Token Index: 725

Text #19

Max Range: 3.7572. Min Range: -3.7572

Max Act: 3.5993. Min Act: -0.1700

Data Index: 1623718 (Python Code)

Max Activating Token Index: 633