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

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

Neuron 1161 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6026. Min Range: -5.6026

Max Act: 5.6026. Min Act: -0.1700

Data Index: 250975 (C4 (Web Text))

Max Activating Token Index: 531

Text #1

Max Range: 5.6026. Min Range: -5.6026

Max Act: 5.5401. Min Act: -0.1700

Data Index: 379876 (C4 (Web Text))

Max Activating Token Index: 466

Text #2

Max Range: 5.6026. Min Range: -5.6026

Max Act: 5.3526. Min Act: -0.1700

Data Index: 454716 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 5.6026. Min Range: -5.6026

Max Act: 5.3213. Min Act: -0.1700

Data Index: 81993 (C4 (Web Text))

Max Activating Token Index: 331

Text #4

Max Range: 5.6026. Min Range: -5.6026

Max Act: 5.2588. Min Act: -0.1700

Data Index: 108270 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 5.6026. Min Range: -5.6026

Max Act: 5.2276. Min Act: -0.1700

Data Index: 588319 (C4 (Web Text))

Max Activating Token Index: 508

Text #6

Max Range: 5.6026. Min Range: -5.6026

Max Act: 5.2276. Min Act: -0.1700

Data Index: 159640 (C4 (Web Text))

Max Activating Token Index: 529

Text #7

Max Range: 5.6026. Min Range: -5.6026

Max Act: 5.1963. Min Act: -0.1700

Data Index: 72607 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 5.6026. Min Range: -5.6026

Max Act: 5.1026. Min Act: -0.1700

Data Index: 367580 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 5.6026. Min Range: -5.6026

Max Act: 5.1338. Min Act: -0.1700

Data Index: 89273 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 5.6026. Min Range: -5.6026

Max Act: 5.1651. Min Act: -0.1700

Data Index: 563367 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 5.6026. Min Range: -5.6026

Max Act: 5.1651. Min Act: -0.1700

Data Index: 881019 (C4 (Web Text))

Max Activating Token Index: 310

Text #12

Max Range: 5.6026. Min Range: -5.6026

Max Act: 5.1963. Min Act: -0.1700

Data Index: 1241075 (C4 (Web Text))

Max Activating Token Index: 732

Text #13

Max Range: 5.6026. Min Range: -5.6026

Max Act: 5.1338. Min Act: -0.1700

Data Index: 827483 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 5.6026. Min Range: -5.6026

Max Act: 5.1338. Min Act: -0.1700

Data Index: 86645 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 5.6026. Min Range: -5.6026

Max Act: 5.0713. Min Act: -0.1700

Data Index: 942007 (C4 (Web Text))

Max Activating Token Index: 472

Text #16

Max Range: 5.6026. Min Range: -5.6026

Max Act: 5.1338. Min Act: -0.1700

Data Index: 141877 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 5.6026. Min Range: -5.6026

Max Act: 5.0713. Min Act: -0.1700

Data Index: 1103255 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 5.6026. Min Range: -5.6026

Max Act: 5.0713. Min Act: -0.1700

Data Index: 46392 (C4 (Web Text))

Max Activating Token Index: 867

Text #19

Max Range: 5.6026. Min Range: -5.6026

Max Act: 5.0401. Min Act: -0.1700

Data Index: 1214938 (C4 (Web Text))

Max Activating Token Index: 346