Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1555 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.7747. Min Range: -3.7747

Max Act: 3.7591. Min Act: -0.1700

Data Index: 364293 (C4 (Web Text))

Max Activating Token Index: 733

Text #1

Max Range: 3.7747. Min Range: -3.7747

Max Act: 3.7747. Min Act: -0.1700

Data Index: 1044229 (C4 (Web Text))

Max Activating Token Index: 683

Text #2

Max Range: 3.7747. Min Range: -3.7747

Max Act: 3.7435. Min Act: -0.1700

Data Index: 622246 (C4 (Web Text))

Max Activating Token Index: 447

Text #3

Max Range: 3.7747. Min Range: -3.7747

Max Act: 3.6965. Min Act: -0.1700

Data Index: 107635 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 3.7747. Min Range: -3.7747

Max Act: 3.7122. Min Act: -0.1700

Data Index: 111763 (C4 (Web Text))

Max Activating Token Index: 631

Text #5

Max Range: 3.7747. Min Range: -3.7747

Max Act: 3.6965. Min Act: -0.1700

Data Index: 556518 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 3.7747. Min Range: -3.7747

Max Act: 3.6809. Min Act: -0.1700

Data Index: 803638 (C4 (Web Text))

Max Activating Token Index: 365

Text #7

Max Range: 3.7747. Min Range: -3.7747

Max Act: 3.6652. Min Act: -0.1700

Data Index: 756897 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 3.7747. Min Range: -3.7747

Max Act: 3.6652. Min Act: -0.1700

Data Index: 700410 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 3.7747. Min Range: -3.7747

Max Act: 3.6496. Min Act: -0.1700

Data Index: 141561 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 3.7747. Min Range: -3.7747

Max Act: 3.6965. Min Act: -0.1700

Data Index: 851997 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 3.7747. Min Range: -3.7747

Max Act: 3.6183. Min Act: -0.1700

Data Index: 1127696 (C4 (Web Text))

Max Activating Token Index: 1021

Text #12

Max Range: 3.7747. Min Range: -3.7747

Max Act: 3.6496. Min Act: -0.1700

Data Index: 510581 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 3.7747. Min Range: -3.7747

Max Act: 3.6339. Min Act: -0.1700

Data Index: 344940 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 3.7747. Min Range: -3.7747

Max Act: 3.6026. Min Act: -0.1700

Data Index: 718084 (C4 (Web Text))

Max Activating Token Index: 492

Text #15

Max Range: 3.7747. Min Range: -3.7747

Max Act: 3.6183. Min Act: -0.1700

Data Index: 240759 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 3.7747. Min Range: -3.7747

Max Act: 3.6652. Min Act: -0.1700

Data Index: 1255753 (C4 (Web Text))

Max Activating Token Index: 232

Text #17

Max Range: 3.7747. Min Range: -3.7747

Max Act: 3.6183. Min Act: -0.1700

Data Index: 1012659 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 3.7747. Min Range: -3.7747

Max Act: 3.5869. Min Act: -0.1700

Data Index: 1145321 (C4 (Web Text))

Max Activating Token Index: 691

Text #19

Max Range: 3.7747. Min Range: -3.7747

Max Act: 3.6026. Min Act: -0.1700

Data Index: 453017 (C4 (Web Text))

Max Activating Token Index: 459