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

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

Neuron 1472 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: 4.2015. Min Range: -4.2015

Max Act: 4.2015. Min Act: -0.1700

Data Index: 1151506 (C4 (Web Text))

Max Activating Token Index: 454

Text #1

Max Range: 4.2015. Min Range: -4.2015

Max Act: 4.0273. Min Act: -0.1700

Data Index: 684177 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 4.2015. Min Range: -4.2015

Max Act: 3.9918. Min Act: -0.1700

Data Index: 867998 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 4.2015. Min Range: -4.2015

Max Act: 3.9658. Min Act: -0.1700

Data Index: 1212960 (C4 (Web Text))

Max Activating Token Index: 258

Text #4

Max Range: 4.2015. Min Range: -4.2015

Max Act: 3.9791. Min Act: -0.1700

Data Index: 371879 (C4 (Web Text))

Max Activating Token Index: 368

Text #5

Max Range: 4.2015. Min Range: -4.2015

Max Act: 3.8783. Min Act: -0.1700

Data Index: 1156995 (C4 (Web Text))

Max Activating Token Index: 734

Text #6

Max Range: 4.2015. Min Range: -4.2015

Max Act: 3.8785. Min Act: -0.1700

Data Index: 269553 (C4 (Web Text))

Max Activating Token Index: 175

Text #7

Max Range: 4.2015. Min Range: -4.2015

Max Act: 3.8438. Min Act: -0.1700

Data Index: 313313 (C4 (Web Text))

Max Activating Token Index: 278

Text #8

Max Range: 4.2015. Min Range: -4.2015

Max Act: 3.8824. Min Act: -0.1700

Data Index: 177872 (C4 (Web Text))

Max Activating Token Index: 978

Text #9

Max Range: 4.2015. Min Range: -4.2015

Max Act: 3.7788. Min Act: -0.1700

Data Index: 993789 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 4.2015. Min Range: -4.2015

Max Act: 3.7972. Min Act: -0.1700

Data Index: 948251 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 4.2015. Min Range: -4.2015

Max Act: 3.7490. Min Act: -0.1700

Data Index: 981429 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 4.2015. Min Range: -4.2015

Max Act: 3.7990. Min Act: -0.1700

Data Index: 498658 (C4 (Web Text))

Max Activating Token Index: 532

Text #13

Max Range: 4.2015. Min Range: -4.2015

Max Act: 3.7797. Min Act: -0.1700

Data Index: 429640 (C4 (Web Text))

Max Activating Token Index: 921

Text #14

Max Range: 4.2015. Min Range: -4.2015

Max Act: 3.7895. Min Act: -0.1700

Data Index: 467584 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 4.2015. Min Range: -4.2015

Max Act: 3.7874. Min Act: -0.1700

Data Index: 1366903 (Python Code)

Max Activating Token Index: 174

Text #16

Max Range: 4.2015. Min Range: -4.2015

Max Act: 3.7895. Min Act: -0.1700

Data Index: 1351640 (C4 (Web Text))

Max Activating Token Index: 395

Text #17

Max Range: 4.2015. Min Range: -4.2015

Max Act: 3.6878. Min Act: -0.1700

Data Index: 1253485 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 4.2015. Min Range: -4.2015

Max Act: 3.7203. Min Act: -0.1700

Data Index: 103794 (C4 (Web Text))

Max Activating Token Index: 670

Text #19

Max Range: 4.2015. Min Range: -4.2015

Max Act: 3.7031. Min Act: -0.1700

Data Index: 882555 (C4 (Web Text))

Max Activating Token Index: 118