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

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

Neuron 766 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: 3.8962. Min Range: -3.8962

Max Act: 3.8650. Min Act: -0.1700

Data Index: 602343 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 3.8962. Min Range: -3.8962

Max Act: 3.8962. Min Act: -0.1700

Data Index: 614844 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 3.8962. Min Range: -3.8962

Max Act: 3.8337. Min Act: -0.1700

Data Index: 660796 (C4 (Web Text))

Max Activating Token Index: 529

Text #3

Max Range: 3.8962. Min Range: -3.8962

Max Act: 3.7711. Min Act: -0.1700

Data Index: 552004 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 3.8962. Min Range: -3.8962

Max Act: 3.7398. Min Act: -0.1700

Data Index: 648213 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 3.8962. Min Range: -3.8962

Max Act: 3.7398. Min Act: -0.1700

Data Index: 296369 (C4 (Web Text))

Max Activating Token Index: 17

Text #6

Max Range: 3.8962. Min Range: -3.8962

Max Act: 3.7085. Min Act: -0.1700

Data Index: 488133 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 3.8962. Min Range: -3.8962

Max Act: 3.6772. Min Act: -0.1700

Data Index: 770457 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 3.8962. Min Range: -3.8962

Max Act: 3.6772. Min Act: -0.1700

Data Index: 1288718 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 3.8962. Min Range: -3.8962

Max Act: 3.6146. Min Act: -0.1700

Data Index: 849422 (C4 (Web Text))

Max Activating Token Index: 587

Text #10

Max Range: 3.8962. Min Range: -3.8962

Max Act: 3.6459. Min Act: -0.1700

Data Index: 893240 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 3.8962. Min Range: -3.8962

Max Act: 3.6459. Min Act: -0.1700

Data Index: 996976 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 3.8962. Min Range: -3.8962

Max Act: 3.6146. Min Act: -0.1700

Data Index: 60288 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 3.8962. Min Range: -3.8962

Max Act: 3.6146. Min Act: -0.1700

Data Index: 438699 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 3.8962. Min Range: -3.8962

Max Act: 3.6146. Min Act: -0.1700

Data Index: 1091527 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 3.8962. Min Range: -3.8962

Max Act: 3.6146. Min Act: -0.1700

Data Index: 928028 (C4 (Web Text))

Max Activating Token Index: 722

Text #16

Max Range: 3.8962. Min Range: -3.8962

Max Act: 3.5833. Min Act: -0.1700

Data Index: 1038507 (C4 (Web Text))

Max Activating Token Index: 117

Text #17

Max Range: 3.8962. Min Range: -3.8962

Max Act: 3.5833. Min Act: -0.1700

Data Index: 667164 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 3.8962. Min Range: -3.8962

Max Act: 3.5520. Min Act: -0.1700

Data Index: 508543 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 3.8962. Min Range: -3.8962

Max Act: 3.5833. Min Act: -0.1700

Data Index: 592977 (C4 (Web Text))

Max Activating Token Index: 39