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

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

Neuron 1609 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5570. Min Range: -3.5570

Max Act: 3.5570. Min Act: -0.1700

Data Index: 802065 (C4 (Web Text))

Max Activating Token Index: 842

Text #1

Max Range: 3.5570. Min Range: -3.5570

Max Act: 3.5413. Min Act: -0.1700

Data Index: 1007355 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 3.5570. Min Range: -3.5570

Max Act: 3.4473. Min Act: -0.1700

Data Index: 1090637 (C4 (Web Text))

Max Activating Token Index: 356

Text #3

Max Range: 3.5570. Min Range: -3.5570

Max Act: 3.4473. Min Act: -0.1700

Data Index: 998161 (C4 (Web Text))

Max Activating Token Index: 295

Text #4

Max Range: 3.5570. Min Range: -3.5570

Max Act: 3.4787. Min Act: -0.1700

Data Index: 29156 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 3.5570. Min Range: -3.5570

Max Act: 3.4003. Min Act: -0.1700

Data Index: 771143 (C4 (Web Text))

Max Activating Token Index: 860

Text #6

Max Range: 3.5570. Min Range: -3.5570

Max Act: 3.4159. Min Act: -0.1700

Data Index: 675885 (C4 (Web Text))

Max Activating Token Index: 531

Text #7

Max Range: 3.5570. Min Range: -3.5570

Max Act: 3.3689. Min Act: -0.1700

Data Index: 984720 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 3.5570. Min Range: -3.5570

Max Act: 3.4003. Min Act: -0.1700

Data Index: 1233006 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 3.5570. Min Range: -3.5570

Max Act: 3.3689. Min Act: -0.1700

Data Index: 766607 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 3.5570. Min Range: -3.5570

Max Act: 3.3532. Min Act: -0.1700

Data Index: 544469 (C4 (Web Text))

Max Activating Token Index: 721

Text #11

Max Range: 3.5570. Min Range: -3.5570

Max Act: 3.3532. Min Act: -0.1700

Data Index: 872987 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 3.5570. Min Range: -3.5570

Max Act: 3.3532. Min Act: -0.1700

Data Index: 546548 (C4 (Web Text))

Max Activating Token Index: 736

Text #13

Max Range: 3.5570. Min Range: -3.5570

Max Act: 3.3375. Min Act: -0.1700

Data Index: 934622 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 3.5570. Min Range: -3.5570

Max Act: 3.3689. Min Act: -0.1700

Data Index: 232193 (C4 (Web Text))

Max Activating Token Index: 231

Text #15

Max Range: 3.5570. Min Range: -3.5570

Max Act: 3.3689. Min Act: -0.1700

Data Index: 954407 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 3.5570. Min Range: -3.5570

Max Act: 3.3846. Min Act: -0.1700

Data Index: 244740 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 3.5570. Min Range: -3.5570

Max Act: 3.3689. Min Act: -0.1700

Data Index: 954327 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 3.5570. Min Range: -3.5570

Max Act: 3.3375. Min Act: -0.1700

Data Index: 821440 (C4 (Web Text))

Max Activating Token Index: 215

Text #19

Max Range: 3.5570. Min Range: -3.5570

Max Act: 3.3375. Min Act: -0.1700

Data Index: 231586 (C4 (Web Text))

Max Activating Token Index: 79