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

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

Neuron 297 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: 7.2074. Min Range: -7.2074

Max Act: 7.2074. Min Act: -0.1700

Data Index: 615377 (C4 (Web Text))

Max Activating Token Index: 640

Text #1

Max Range: 7.2074. Min Range: -7.2074

Max Act: 7.0199. Min Act: -0.1700

Data Index: 995292 (C4 (Web Text))

Max Activating Token Index: 247

Text #2

Max Range: 7.2074. Min Range: -7.2074

Max Act: 6.8011. Min Act: -0.1700

Data Index: 793076 (C4 (Web Text))

Max Activating Token Index: 434

Text #3

Max Range: 7.2074. Min Range: -7.2074

Max Act: 6.8011. Min Act: -0.1700

Data Index: 801010 (C4 (Web Text))

Max Activating Token Index: 333

Text #4

Max Range: 7.2074. Min Range: -7.2074

Max Act: 6.8011. Min Act: -0.1700

Data Index: 1197323 (C4 (Web Text))

Max Activating Token Index: 614

Text #5

Max Range: 7.2074. Min Range: -7.2074

Max Act: 6.6918. Min Act: -0.1700

Data Index: 1135517 (C4 (Web Text))

Max Activating Token Index: 517

Text #6

Max Range: 7.2074. Min Range: -7.2074

Max Act: 6.7230. Min Act: -0.1700

Data Index: 885383 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 7.2074. Min Range: -7.2074

Max Act: 6.6605. Min Act: -0.1700

Data Index: 1325926 (C4 (Web Text))

Max Activating Token Index: 225

Text #8

Max Range: 7.2074. Min Range: -7.2074

Max Act: 6.6449. Min Act: -0.1700

Data Index: 638978 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 7.2074. Min Range: -7.2074

Max Act: 6.5668. Min Act: -0.1700

Data Index: 950633 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 7.2074. Min Range: -7.2074

Max Act: 6.5824. Min Act: -0.1700

Data Index: 371731 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 7.2074. Min Range: -7.2074

Max Act: 6.6293. Min Act: -0.1700

Data Index: 992022 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 7.2074. Min Range: -7.2074

Max Act: 6.5199. Min Act: -0.1700

Data Index: 618350 (C4 (Web Text))

Max Activating Token Index: 287

Text #13

Max Range: 7.2074. Min Range: -7.2074

Max Act: 6.5511. Min Act: -0.1700

Data Index: 531289 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 7.2074. Min Range: -7.2074

Max Act: 6.4418. Min Act: -0.1700

Data Index: 604069 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 7.2074. Min Range: -7.2074

Max Act: 6.5043. Min Act: -0.1700

Data Index: 1051214 (C4 (Web Text))

Max Activating Token Index: 948

Text #16

Max Range: 7.2074. Min Range: -7.2074

Max Act: 6.5199. Min Act: -0.1700

Data Index: 1309519 (C4 (Web Text))

Max Activating Token Index: 839

Text #17

Max Range: 7.2074. Min Range: -7.2074

Max Act: 6.4418. Min Act: -0.1700

Data Index: 978318 (C4 (Web Text))

Max Activating Token Index: 91

Text #18

Max Range: 7.2074. Min Range: -7.2074

Max Act: 6.5043. Min Act: -0.1700

Data Index: 813925 (C4 (Web Text))

Max Activating Token Index: 398

Text #19

Max Range: 7.2074. Min Range: -7.2074

Max Act: 6.3949. Min Act: -0.1700

Data Index: 184940 (C4 (Web Text))

Max Activating Token Index: 871