Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 879 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.8628. Min Range: -5.8628

Max Act: 5.8628. Min Act: -0.1700

Data Index: 1119215 (C4 (Web Text))

Max Activating Token Index: 663

Text #1

Max Range: 5.8628. Min Range: -5.8628

Max Act: 5.6753. Min Act: -0.1700

Data Index: 954943 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 5.8628. Min Range: -5.8628

Max Act: 5.6440. Min Act: -0.1700

Data Index: 471229 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 5.8628. Min Range: -5.8628

Max Act: 5.6440. Min Act: -0.1700

Data Index: 1195306 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 5.8628. Min Range: -5.8628

Max Act: 5.6128. Min Act: -0.1700

Data Index: 529082 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 5.8628. Min Range: -5.8628

Max Act: 5.5815. Min Act: -0.1700

Data Index: 1236481 (C4 (Web Text))

Max Activating Token Index: 757

Text #6

Max Range: 5.8628. Min Range: -5.8628

Max Act: 5.5190. Min Act: -0.1700

Data Index: 618985 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 5.8628. Min Range: -5.8628

Max Act: 5.5815. Min Act: -0.1700

Data Index: 322751 (C4 (Web Text))

Max Activating Token Index: 169

Text #8

Max Range: 5.8628. Min Range: -5.8628

Max Act: 5.5503. Min Act: -0.1700

Data Index: 659853 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 5.8628. Min Range: -5.8628

Max Act: 5.4878. Min Act: -0.1700

Data Index: 1252872 (C4 (Web Text))

Max Activating Token Index: 178

Text #10

Max Range: 5.8628. Min Range: -5.8628

Max Act: 5.4565. Min Act: -0.1700

Data Index: 353311 (C4 (Web Text))

Max Activating Token Index: 92

Text #11

Max Range: 5.8628. Min Range: -5.8628

Max Act: 5.4565. Min Act: -0.1700

Data Index: 1077791 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 5.8628. Min Range: -5.8628

Max Act: 5.4565. Min Act: -0.1700

Data Index: 600720 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 5.8628. Min Range: -5.8628

Max Act: 5.3628. Min Act: -0.1700

Data Index: 841391 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 5.8628. Min Range: -5.8628

Max Act: 5.4253. Min Act: -0.1700

Data Index: 182667 (C4 (Web Text))

Max Activating Token Index: 526

Text #15

Max Range: 5.8628. Min Range: -5.8628

Max Act: 5.4253. Min Act: -0.1700

Data Index: 1015556 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 5.8628. Min Range: -5.8628

Max Act: 5.3940. Min Act: -0.1700

Data Index: 544236 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 5.8628. Min Range: -5.8628

Max Act: 5.3628. Min Act: -0.1700

Data Index: 819674 (C4 (Web Text))

Max Activating Token Index: 427

Text #18

Max Range: 5.8628. Min Range: -5.8628

Max Act: 5.3003. Min Act: -0.1700

Data Index: 390390 (C4 (Web Text))

Max Activating Token Index: 59

Text #19

Max Range: 5.8628. Min Range: -5.8628

Max Act: 5.3628. Min Act: -0.1700

Data Index: 233525 (C4 (Web Text))

Max Activating Token Index: 474