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

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

Neuron 1160 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: 3.7342. Min Range: -3.7342

Max Act: 3.7342. Min Act: -0.1700

Data Index: 648651 (C4 (Web Text))

Max Activating Token Index: 685

Text #1

Max Range: 3.7342. Min Range: -3.7342

Max Act: 3.5777. Min Act: -0.1700

Data Index: 1225994 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 3.7342. Min Range: -3.7342

Max Act: 3.5777. Min Act: -0.1700

Data Index: 231053 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 3.7342. Min Range: -3.7342

Max Act: 3.5464. Min Act: -0.1700

Data Index: 343016 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 3.7342. Min Range: -3.7342

Max Act: 3.5464. Min Act: -0.1700

Data Index: 1036390 (C4 (Web Text))

Max Activating Token Index: 323

Text #5

Max Range: 3.7342. Min Range: -3.7342

Max Act: 3.4994. Min Act: -0.1700

Data Index: 580091 (C4 (Web Text))

Max Activating Token Index: 926

Text #6

Max Range: 3.7342. Min Range: -3.7342

Max Act: 3.4210. Min Act: -0.1700

Data Index: 1346410 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 3.7342. Min Range: -3.7342

Max Act: 3.4210. Min Act: -0.1700

Data Index: 622218 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 3.7342. Min Range: -3.7342

Max Act: 3.4210. Min Act: -0.1700

Data Index: 1306398 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 3.7342. Min Range: -3.7342

Max Act: 3.4210. Min Act: -0.1700

Data Index: 862724 (C4 (Web Text))

Max Activating Token Index: 593

Text #10

Max Range: 3.7342. Min Range: -3.7342

Max Act: 3.4053. Min Act: -0.1700

Data Index: 733012 (C4 (Web Text))

Max Activating Token Index: 885

Text #11

Max Range: 3.7342. Min Range: -3.7342

Max Act: 3.4210. Min Act: -0.1700

Data Index: 620868 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 3.7342. Min Range: -3.7342

Max Act: 3.4053. Min Act: -0.1700

Data Index: 549037 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 3.7342. Min Range: -3.7342

Max Act: 3.3740. Min Act: -0.1700

Data Index: 1202352 (C4 (Web Text))

Max Activating Token Index: 980

Text #14

Max Range: 3.7342. Min Range: -3.7342

Max Act: 3.3896. Min Act: -0.1700

Data Index: 1318417 (C4 (Web Text))

Max Activating Token Index: 670

Text #15

Max Range: 3.7342. Min Range: -3.7342

Max Act: 3.3896. Min Act: -0.1700

Data Index: 975785 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 3.7342. Min Range: -3.7342

Max Act: 3.3896. Min Act: -0.1700

Data Index: 484736 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 3.7342. Min Range: -3.7342

Max Act: 3.3896. Min Act: -0.1700

Data Index: 29836 (C4 (Web Text))

Max Activating Token Index: 866

Text #18

Max Range: 3.7342. Min Range: -3.7342

Max Act: 3.3583. Min Act: -0.1700

Data Index: 855734 (C4 (Web Text))

Max Activating Token Index: 600

Text #19

Max Range: 3.7342. Min Range: -3.7342

Max Act: 3.3583. Min Act: -0.1700

Data Index: 1216602 (C4 (Web Text))

Max Activating Token Index: 729