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

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

Neuron 265 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: 3.3138. Min Range: -3.3138

Max Act: 3.3138. Min Act: -0.1700

Data Index: 650942 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 3.3138. Min Range: -3.3138

Max Act: 3.2981. Min Act: -0.1700

Data Index: 579230 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 3.3138. Min Range: -3.3138

Max Act: 3.2667. Min Act: -0.1700

Data Index: 100657 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 3.3138. Min Range: -3.3138

Max Act: 3.2195. Min Act: -0.1700

Data Index: 13265 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 3.3138. Min Range: -3.3138

Max Act: 3.2195. Min Act: -0.1700

Data Index: 1333325 (C4 (Web Text))

Max Activating Token Index: 943

Text #5

Max Range: 3.3138. Min Range: -3.3138

Max Act: 3.2038. Min Act: -0.1700

Data Index: 335142 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 3.3138. Min Range: -3.3138

Max Act: 3.2038. Min Act: -0.1700

Data Index: 126708 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 3.3138. Min Range: -3.3138

Max Act: 3.1723. Min Act: -0.1700

Data Index: 1303127 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 3.3138. Min Range: -3.3138

Max Act: 3.2038. Min Act: -0.1700

Data Index: 661053 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 3.3138. Min Range: -3.3138

Max Act: 3.2038. Min Act: -0.1700

Data Index: 444612 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 3.3138. Min Range: -3.3138

Max Act: 3.1881. Min Act: -0.1700

Data Index: 1318931 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 3.3138. Min Range: -3.3138

Max Act: 3.1881. Min Act: -0.1698

Data Index: 1077615 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 3.3138. Min Range: -3.3138

Max Act: 3.1723. Min Act: -0.1699

Data Index: 923499 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 3.3138. Min Range: -3.3138

Max Act: 3.1723. Min Act: -0.1700

Data Index: 907777 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 3.3138. Min Range: -3.3138

Max Act: 3.1566. Min Act: -0.1700

Data Index: 1244966 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 3.3138. Min Range: -3.3138

Max Act: 3.1723. Min Act: -0.1700

Data Index: 382192 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 3.3138. Min Range: -3.3138

Max Act: 3.1566. Min Act: -0.1700

Data Index: 1275942 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 3.3138. Min Range: -3.3138

Max Act: 3.1566. Min Act: -0.1700

Data Index: 606892 (C4 (Web Text))

Max Activating Token Index: 509

Text #18

Max Range: 3.3138. Min Range: -3.3138

Max Act: 3.1566. Min Act: -0.1700

Data Index: 1435518 (Python Code)

Max Activating Token Index: 685

Text #19

Max Range: 3.3138. Min Range: -3.3138

Max Act: 3.1409. Min Act: -0.1700

Data Index: 813593 (C4 (Web Text))

Max Activating Token Index: 790