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

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

Neuron 892 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: 5.0596. Min Range: -5.0596

Max Act: 5.0596. Min Act: -0.1700

Data Index: 812714 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 5.0596. Min Range: -5.0596

Max Act: 5.0283. Min Act: -0.1700

Data Index: 64603 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 5.0596. Min Range: -5.0596

Max Act: 4.9658. Min Act: -0.1700

Data Index: 773023 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 5.0596. Min Range: -5.0596

Max Act: 4.9814. Min Act: -0.1700

Data Index: 1115237 (C4 (Web Text))

Max Activating Token Index: 53

Text #4

Max Range: 5.0596. Min Range: -5.0596

Max Act: 4.9502. Min Act: -0.1700

Data Index: 853355 (C4 (Web Text))

Max Activating Token Index: 626

Text #5

Max Range: 5.0596. Min Range: -5.0596

Max Act: 4.9033. Min Act: -0.1700

Data Index: 164875 (C4 (Web Text))

Max Activating Token Index: 946

Text #6

Max Range: 5.0596. Min Range: -5.0596

Max Act: 4.9033. Min Act: -0.1700

Data Index: 757607 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 5.0596. Min Range: -5.0596

Max Act: 4.8877. Min Act: -0.1700

Data Index: 374159 (C4 (Web Text))

Max Activating Token Index: 909

Text #8

Max Range: 5.0596. Min Range: -5.0596

Max Act: 4.8564. Min Act: -0.1700

Data Index: 607006 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 5.0596. Min Range: -5.0596

Max Act: 4.8252. Min Act: -0.1700

Data Index: 1293480 (C4 (Web Text))

Max Activating Token Index: 295

Text #10

Max Range: 5.0596. Min Range: -5.0596

Max Act: 4.8721. Min Act: -0.1700

Data Index: 332487 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 5.0596. Min Range: -5.0596

Max Act: 4.7783. Min Act: -0.1700

Data Index: 1130720 (C4 (Web Text))

Max Activating Token Index: 730

Text #12

Max Range: 5.0596. Min Range: -5.0596

Max Act: 4.8408. Min Act: -0.1700

Data Index: 1041698 (C4 (Web Text))

Max Activating Token Index: 254

Text #13

Max Range: 5.0596. Min Range: -5.0596

Max Act: 4.8408. Min Act: -0.1700

Data Index: 513484 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 5.0596. Min Range: -5.0596

Max Act: 4.8252. Min Act: -0.1700

Data Index: 1099870 (C4 (Web Text))

Max Activating Token Index: 956

Text #15

Max Range: 5.0596. Min Range: -5.0596

Max Act: 4.8096. Min Act: -0.1700

Data Index: 1214947 (C4 (Web Text))

Max Activating Token Index: 529

Text #16

Max Range: 5.0596. Min Range: -5.0596

Max Act: 4.7627. Min Act: -0.1700

Data Index: 7680 (C4 (Web Text))

Max Activating Token Index: 480

Text #17

Max Range: 5.0596. Min Range: -5.0596

Max Act: 4.8096. Min Act: -0.1700

Data Index: 424617 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 5.0596. Min Range: -5.0596

Max Act: 4.7471. Min Act: -0.1700

Data Index: 384071 (C4 (Web Text))

Max Activating Token Index: 110

Text #19

Max Range: 5.0596. Min Range: -5.0596

Max Act: 4.7627. Min Act: -0.1700

Data Index: 1335629 (C4 (Web Text))

Max Activating Token Index: 203