Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 270 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.6909. Min Range: -3.6909

Max Act: 3.6909. Min Act: -0.1700

Data Index: 1359222 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 3.6909. Min Range: -3.6909

Max Act: 3.6752. Min Act: -0.1700

Data Index: 925239 (C4 (Web Text))

Max Activating Token Index: 706

Text #2

Max Range: 3.6909. Min Range: -3.6909

Max Act: 3.6752. Min Act: -0.1700

Data Index: 1146505 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 3.6909. Min Range: -3.6909

Max Act: 3.6439. Min Act: -0.1700

Data Index: 889848 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 3.6909. Min Range: -3.6909

Max Act: 3.6596. Min Act: -0.1700

Data Index: 863993 (C4 (Web Text))

Max Activating Token Index: 253

Text #5

Max Range: 3.6909. Min Range: -3.6909

Max Act: 3.6439. Min Act: -0.1700

Data Index: 538943 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 3.6909. Min Range: -3.6909

Max Act: 3.5970. Min Act: -0.1700

Data Index: 541085 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 3.6909. Min Range: -3.6909

Max Act: 3.6126. Min Act: -0.1700

Data Index: 255751 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 3.6909. Min Range: -3.6909

Max Act: 3.6126. Min Act: -0.1700

Data Index: 686881 (C4 (Web Text))

Max Activating Token Index: 761

Text #9

Max Range: 3.6909. Min Range: -3.6909

Max Act: 3.6126. Min Act: -0.1700

Data Index: 422440 (C4 (Web Text))

Max Activating Token Index: 302

Text #10

Max Range: 3.6909. Min Range: -3.6909

Max Act: 3.5970. Min Act: -0.1700

Data Index: 80553 (C4 (Web Text))

Max Activating Token Index: 611

Text #11

Max Range: 3.6909. Min Range: -3.6909

Max Act: 3.5970. Min Act: -0.1700

Data Index: 1009846 (C4 (Web Text))

Max Activating Token Index: 49

Text #12

Max Range: 3.6909. Min Range: -3.6909

Max Act: 3.5813. Min Act: -0.1700

Data Index: 963076 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 3.6909. Min Range: -3.6909

Max Act: 3.5813. Min Act: -0.1700

Data Index: 859841 (C4 (Web Text))

Max Activating Token Index: 312

Text #14

Max Range: 3.6909. Min Range: -3.6909

Max Act: 3.5500. Min Act: -0.1700

Data Index: 908234 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 3.6909. Min Range: -3.6909

Max Act: 3.5656. Min Act: -0.1700

Data Index: 1210027 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 3.6909. Min Range: -3.6909

Max Act: 3.5656. Min Act: -0.1700

Data Index: 507485 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 3.6909. Min Range: -3.6909

Max Act: 3.5500. Min Act: -0.1700

Data Index: 300210 (C4 (Web Text))

Max Activating Token Index: 615

Text #18

Max Range: 3.6909. Min Range: -3.6909

Max Act: 3.5656. Min Act: -0.1700

Data Index: 676405 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 3.6909. Min Range: -3.6909

Max Act: 3.5656. Min Act: -0.1700

Data Index: 505659 (C4 (Web Text))

Max Activating Token Index: 925