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

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

Neuron 1182 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.2883. Min Range: -3.2883

Max Act: 3.2883. Min Act: -0.1700

Data Index: 431261 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 3.2883. Min Range: -3.2883

Max Act: 3.2883. Min Act: -0.1700

Data Index: 415663 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 3.2883. Min Range: -3.2883

Max Act: 3.2254. Min Act: -0.1700

Data Index: 754084 (C4 (Web Text))

Max Activating Token Index: 338

Text #3

Max Range: 3.2883. Min Range: -3.2883

Max Act: 3.1940. Min Act: -0.1700

Data Index: 574379 (C4 (Web Text))

Max Activating Token Index: 717

Text #4

Max Range: 3.2883. Min Range: -3.2883

Max Act: 3.2254. Min Act: -0.1700

Data Index: 841359 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 3.2883. Min Range: -3.2883

Max Act: 3.1940. Min Act: -0.1700

Data Index: 893304 (C4 (Web Text))

Max Activating Token Index: 335

Text #6

Max Range: 3.2883. Min Range: -3.2883

Max Act: 3.1940. Min Act: -0.1700

Data Index: 550760 (C4 (Web Text))

Max Activating Token Index: 446

Text #7

Max Range: 3.2883. Min Range: -3.2883

Max Act: 3.1940. Min Act: -0.1700

Data Index: 1349550 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 3.2883. Min Range: -3.2883

Max Act: 3.1625. Min Act: -0.1700

Data Index: 205841 (C4 (Web Text))

Max Activating Token Index: 317

Text #9

Max Range: 3.2883. Min Range: -3.2883

Max Act: 3.1625. Min Act: -0.1700

Data Index: 1094970 (C4 (Web Text))

Max Activating Token Index: 178

Text #10

Max Range: 3.2883. Min Range: -3.2883

Max Act: 3.1625. Min Act: -0.1700

Data Index: 201131 (C4 (Web Text))

Max Activating Token Index: 407

Text #11

Max Range: 3.2883. Min Range: -3.2883

Max Act: 3.1468. Min Act: -0.1700

Data Index: 1166750 (C4 (Web Text))

Max Activating Token Index: 621

Text #12

Max Range: 3.2883. Min Range: -3.2883

Max Act: 3.1468. Min Act: -0.1700

Data Index: 942236 (C4 (Web Text))

Max Activating Token Index: 761

Text #13

Max Range: 3.2883. Min Range: -3.2883

Max Act: 3.1625. Min Act: -0.1700

Data Index: 1117463 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 3.2883. Min Range: -3.2883

Max Act: 3.1310. Min Act: -0.1700

Data Index: 222098 (C4 (Web Text))

Max Activating Token Index: 772

Text #15

Max Range: 3.2883. Min Range: -3.2883

Max Act: 3.1625. Min Act: -0.1700

Data Index: 918155 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 3.2883. Min Range: -3.2883

Max Act: 3.0995. Min Act: -0.1700

Data Index: 308188 (C4 (Web Text))

Max Activating Token Index: 453

Text #17

Max Range: 3.2883. Min Range: -3.2883

Max Act: 3.1152. Min Act: -0.1700

Data Index: 187179 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 3.2883. Min Range: -3.2883

Max Act: 3.1152. Min Act: -0.1700

Data Index: 75499 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 3.2883. Min Range: -3.2883

Max Act: 3.1310. Min Act: -0.1700

Data Index: 267900 (C4 (Web Text))

Max Activating Token Index: 897