Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 968 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.5353. Min Range: -5.5353

Max Act: 5.5353. Min Act: -0.1700

Data Index: 191726 (C4 (Web Text))

Max Activating Token Index: 359

Text #1

Max Range: 5.5353. Min Range: -5.5353

Max Act: 5.3478. Min Act: -0.1700

Data Index: 1217804 (C4 (Web Text))

Max Activating Token Index: 523

Text #2

Max Range: 5.5353. Min Range: -5.5353

Max Act: 5.2540. Min Act: -0.1700

Data Index: 540124 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 5.5353. Min Range: -5.5353

Max Act: 5.3165. Min Act: -0.1700

Data Index: 761602 (C4 (Web Text))

Max Activating Token Index: 708

Text #4

Max Range: 5.5353. Min Range: -5.5353

Max Act: 5.2540. Min Act: -0.1700

Data Index: 234605 (C4 (Web Text))

Max Activating Token Index: 983

Text #5

Max Range: 5.5353. Min Range: -5.5353

Max Act: 5.2228. Min Act: -0.1700

Data Index: 1074484 (C4 (Web Text))

Max Activating Token Index: 907

Text #6

Max Range: 5.5353. Min Range: -5.5353

Max Act: 5.2228. Min Act: -0.1700

Data Index: 508117 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 5.5353. Min Range: -5.5353

Max Act: 5.1603. Min Act: -0.1700

Data Index: 1355717 (C4 (Web Text))

Max Activating Token Index: 360

Text #8

Max Range: 5.5353. Min Range: -5.5353

Max Act: 5.1290. Min Act: -0.1700

Data Index: 436901 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 5.5353. Min Range: -5.5353

Max Act: 5.0978. Min Act: -0.1700

Data Index: 1012022 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 5.5353. Min Range: -5.5353

Max Act: 5.0665. Min Act: -0.1700

Data Index: 542609 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 5.5353. Min Range: -5.5353

Max Act: 5.0978. Min Act: -0.1700

Data Index: 507125 (C4 (Web Text))

Max Activating Token Index: 724

Text #12

Max Range: 5.5353. Min Range: -5.5353

Max Act: 5.0978. Min Act: -0.1700

Data Index: 115793 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 5.5353. Min Range: -5.5353

Max Act: 5.0978. Min Act: -0.1700

Data Index: 433394 (C4 (Web Text))

Max Activating Token Index: 437

Text #14

Max Range: 5.5353. Min Range: -5.5353

Max Act: 5.0665. Min Act: -0.1700

Data Index: 381815 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 5.5353. Min Range: -5.5353

Max Act: 5.0978. Min Act: -0.1700

Data Index: 1207728 (C4 (Web Text))

Max Activating Token Index: 810

Text #16

Max Range: 5.5353. Min Range: -5.5353

Max Act: 5.0665. Min Act: -0.1700

Data Index: 1030677 (C4 (Web Text))

Max Activating Token Index: 784

Text #17

Max Range: 5.5353. Min Range: -5.5353

Max Act: 5.0665. Min Act: -0.1700

Data Index: 1069973 (C4 (Web Text))

Max Activating Token Index: 914

Text #18

Max Range: 5.5353. Min Range: -5.5353

Max Act: 5.0353. Min Act: -0.1700

Data Index: 380631 (C4 (Web Text))

Max Activating Token Index: 475

Text #19

Max Range: 5.5353. Min Range: -5.5353

Max Act: 5.0353. Min Act: -0.1700

Data Index: 1081675 (C4 (Web Text))

Max Activating Token Index: 785