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

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

Neuron 1846 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: 4.1106. Min Range: -4.1106

Max Act: 4.1106. Min Act: -0.1699

Data Index: 150136 (C4 (Web Text))

Max Activating Token Index: 706

Text #1

Max Range: 4.1106. Min Range: -4.1106

Max Act: 4.1012. Min Act: -0.1699

Data Index: 469335 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 4.1106. Min Range: -4.1106

Max Act: 4.0463. Min Act: -0.1700

Data Index: 872745 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 4.1106. Min Range: -4.1106

Max Act: 4.0418. Min Act: -0.1700

Data Index: 1393231 (Python Code)

Max Activating Token Index: 277

Text #4

Max Range: 4.1106. Min Range: -4.1106

Max Act: 4.0289. Min Act: -0.1699

Data Index: 1359698 (C4 (Web Text))

Max Activating Token Index: 783

Text #5

Max Range: 4.1106. Min Range: -4.1106

Max Act: 3.9596. Min Act: -0.1700

Data Index: 604495 (C4 (Web Text))

Max Activating Token Index: 754

Text #6

Max Range: 4.1106. Min Range: -4.1106

Max Act: 3.9537. Min Act: -0.1700

Data Index: 1250092 (C4 (Web Text))

Max Activating Token Index: 456

Text #7

Max Range: 4.1106. Min Range: -4.1106

Max Act: 3.9654. Min Act: -0.1699

Data Index: 1609832 (Python Code)

Max Activating Token Index: 741

Text #8

Max Range: 4.1106. Min Range: -4.1106

Max Act: 3.9210. Min Act: -0.1700

Data Index: 297313 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 4.1106. Min Range: -4.1106

Max Act: 3.9343. Min Act: -0.1699

Data Index: 767499 (C4 (Web Text))

Max Activating Token Index: 233

Text #10

Max Range: 4.1106. Min Range: -4.1106

Max Act: 3.9426. Min Act: -0.1699

Data Index: 601292 (C4 (Web Text))

Max Activating Token Index: 503

Text #11

Max Range: 4.1106. Min Range: -4.1106

Max Act: 3.9100. Min Act: -0.1700

Data Index: 1191444 (C4 (Web Text))

Max Activating Token Index: 954

Text #12

Max Range: 4.1106. Min Range: -4.1106

Max Act: 3.8936. Min Act: -0.1697

Data Index: 250485 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 4.1106. Min Range: -4.1106

Max Act: 3.8767. Min Act: -0.1700

Data Index: 1032878 (C4 (Web Text))

Max Activating Token Index: 747

Text #14

Max Range: 4.1106. Min Range: -4.1106

Max Act: 3.8842. Min Act: -0.1700

Data Index: 201815 (C4 (Web Text))

Max Activating Token Index: 654

Text #15

Max Range: 4.1106. Min Range: -4.1106

Max Act: 3.8622. Min Act: -0.1699

Data Index: 172088 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 4.1106. Min Range: -4.1106

Max Act: 3.8524. Min Act: -0.1700

Data Index: 413995 (C4 (Web Text))

Max Activating Token Index: 460

Text #17

Max Range: 4.1106. Min Range: -4.1106

Max Act: 3.8736. Min Act: -0.1698

Data Index: 810471 (C4 (Web Text))

Max Activating Token Index: 909

Text #18

Max Range: 4.1106. Min Range: -4.1106

Max Act: 3.8227. Min Act: -0.1700

Data Index: 1387539 (Python Code)

Max Activating Token Index: 292

Text #19

Max Range: 4.1106. Min Range: -4.1106

Max Act: 3.8228. Min Act: -0.1638

Data Index: 669031 (C4 (Web Text))

Max Activating Token Index: 918