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

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

Neuron 1036 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: 11.0475. Min Range: -11.0475

Max Act: 11.0475. Min Act: -0.1699

Data Index: 55036 (C4 (Web Text))

Max Activating Token Index: 295

Text #1

Max Range: 11.0475. Min Range: -11.0475

Max Act: 11.0475. Min Act: -0.1700

Data Index: 436458 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 11.0475. Min Range: -11.0475

Max Act: 10.8600. Min Act: -0.1700

Data Index: 395036 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 11.0475. Min Range: -11.0475

Max Act: 10.6725. Min Act: -0.1700

Data Index: 190481 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 11.0475. Min Range: -11.0475

Max Act: 10.4850. Min Act: -0.1700

Data Index: 723423 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 11.0475. Min Range: -11.0475

Max Act: 10.5475. Min Act: -0.1700

Data Index: 733212 (C4 (Web Text))

Max Activating Token Index: 251

Text #6

Max Range: 11.0475. Min Range: -11.0475

Max Act: 10.5475. Min Act: -0.1700

Data Index: 675289 (C4 (Web Text))

Max Activating Token Index: 565

Text #7

Max Range: 11.0475. Min Range: -11.0475

Max Act: 10.4850. Min Act: -0.1700

Data Index: 281270 (C4 (Web Text))

Max Activating Token Index: 821

Text #8

Max Range: 11.0475. Min Range: -11.0475

Max Act: 10.4850. Min Act: -0.1700

Data Index: 185377 (C4 (Web Text))

Max Activating Token Index: 170

Text #9

Max Range: 11.0475. Min Range: -11.0475

Max Act: 10.4225. Min Act: -0.1700

Data Index: 1178090 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 11.0475. Min Range: -11.0475

Max Act: 10.3600. Min Act: -0.1700

Data Index: 990018 (C4 (Web Text))

Max Activating Token Index: 470

Text #11

Max Range: 11.0475. Min Range: -11.0475

Max Act: 10.3600. Min Act: -0.1700

Data Index: 898665 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 11.0475. Min Range: -11.0475

Max Act: 10.2975. Min Act: -0.1700

Data Index: 1101965 (C4 (Web Text))

Max Activating Token Index: 377

Text #13

Max Range: 11.0475. Min Range: -11.0475

Max Act: 10.5475. Min Act: -0.1700

Data Index: 125337 (C4 (Web Text))

Max Activating Token Index: 896

Text #14

Max Range: 11.0475. Min Range: -11.0475

Max Act: 10.2975. Min Act: -0.1700

Data Index: 1457311 (Python Code)

Max Activating Token Index: 370

Text #15

Max Range: 11.0475. Min Range: -11.0475

Max Act: 10.2975. Min Act: -0.1699

Data Index: 710307 (C4 (Web Text))

Max Activating Token Index: 143

Text #16

Max Range: 11.0475. Min Range: -11.0475

Max Act: 10.2350. Min Act: -0.1700

Data Index: 1104055 (C4 (Web Text))

Max Activating Token Index: 867

Text #17

Max Range: 11.0475. Min Range: -11.0475

Max Act: 10.2975. Min Act: -0.1697

Data Index: 97611 (C4 (Web Text))

Max Activating Token Index: 915

Text #18

Max Range: 11.0475. Min Range: -11.0475

Max Act: 10.2350. Min Act: -0.1700

Data Index: 351735 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 11.0475. Min Range: -11.0475

Max Act: 10.2350. Min Act: -0.1700

Data Index: 967089 (C4 (Web Text))

Max Activating Token Index: 952