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

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

Neuron 205 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: 3.4226. Min Range: -3.4226

Max Act: 3.4226. Min Act: -0.1700

Data Index: 890733 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 3.4226. Min Range: -3.4226

Max Act: 3.3913. Min Act: -0.1700

Data Index: 181358 (C4 (Web Text))

Max Activating Token Index: 653

Text #2

Max Range: 3.4226. Min Range: -3.4226

Max Act: 3.3599. Min Act: -0.1700

Data Index: 1016054 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 3.4226. Min Range: -3.4226

Max Act: 3.3285. Min Act: -0.1700

Data Index: 1177417 (C4 (Web Text))

Max Activating Token Index: 754

Text #4

Max Range: 3.4226. Min Range: -3.4226

Max Act: 3.3285. Min Act: -0.1700

Data Index: 753162 (C4 (Web Text))

Max Activating Token Index: 731

Text #5

Max Range: 3.4226. Min Range: -3.4226

Max Act: 3.2971. Min Act: -0.1700

Data Index: 739054 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 3.4226. Min Range: -3.4226

Max Act: 3.3128. Min Act: -0.1700

Data Index: 1160387 (C4 (Web Text))

Max Activating Token Index: 541

Text #7

Max Range: 3.4226. Min Range: -3.4226

Max Act: 3.3128. Min Act: -0.1700

Data Index: 545371 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 3.4226. Min Range: -3.4226

Max Act: 3.2971. Min Act: -0.1700

Data Index: 100881 (C4 (Web Text))

Max Activating Token Index: 675

Text #9

Max Range: 3.4226. Min Range: -3.4226

Max Act: 3.2814. Min Act: -0.1700

Data Index: 492604 (C4 (Web Text))

Max Activating Token Index: 858

Text #10

Max Range: 3.4226. Min Range: -3.4226

Max Act: 3.2814. Min Act: -0.1700

Data Index: 720118 (C4 (Web Text))

Max Activating Token Index: 302

Text #11

Max Range: 3.4226. Min Range: -3.4226

Max Act: 3.2814. Min Act: -0.1700

Data Index: 222627 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 3.4226. Min Range: -3.4226

Max Act: 3.2971. Min Act: -0.1700

Data Index: 953881 (C4 (Web Text))

Max Activating Token Index: 204

Text #13

Max Range: 3.4226. Min Range: -3.4226

Max Act: 3.2814. Min Act: -0.1700

Data Index: 89717 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 3.4226. Min Range: -3.4226

Max Act: 3.2657. Min Act: -0.1700

Data Index: 653971 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 3.4226. Min Range: -3.4226

Max Act: 3.2657. Min Act: -0.1700

Data Index: 557719 (C4 (Web Text))

Max Activating Token Index: 650

Text #16

Max Range: 3.4226. Min Range: -3.4226

Max Act: 3.2499. Min Act: -0.1700

Data Index: 368078 (C4 (Web Text))

Max Activating Token Index: 776

Text #17

Max Range: 3.4226. Min Range: -3.4226

Max Act: 3.2499. Min Act: -0.1700

Data Index: 830439 (C4 (Web Text))

Max Activating Token Index: 909

Text #18

Max Range: 3.4226. Min Range: -3.4226

Max Act: 3.2499. Min Act: -0.1700

Data Index: 867099 (C4 (Web Text))

Max Activating Token Index: 977

Text #19

Max Range: 3.4226. Min Range: -3.4226

Max Act: 3.2499. Min Act: -0.1700

Data Index: 994338 (C4 (Web Text))

Max Activating Token Index: 552