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

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

Neuron 2002 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.7182. Min Range: -7.7182

Max Act: 7.7182. Min Act: -0.1700

Data Index: 1092199 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 7.7182. Min Range: -7.7182

Max Act: 7.5932. Min Act: -0.1700

Data Index: 872593 (C4 (Web Text))

Max Activating Token Index: 446

Text #2

Max Range: 7.7182. Min Range: -7.7182

Max Act: 7.5932. Min Act: -0.1700

Data Index: 718520 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 7.7182. Min Range: -7.7182

Max Act: 7.5307. Min Act: -0.1700

Data Index: 807251 (C4 (Web Text))

Max Activating Token Index: 694

Text #4

Max Range: 7.7182. Min Range: -7.7182

Max Act: 7.6244. Min Act: -0.1700

Data Index: 1298173 (C4 (Web Text))

Max Activating Token Index: 727

Text #5

Max Range: 7.7182. Min Range: -7.7182

Max Act: 7.4994. Min Act: -0.1700

Data Index: 544008 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 7.7182. Min Range: -7.7182

Max Act: 7.5932. Min Act: -0.1700

Data Index: 629346 (C4 (Web Text))

Max Activating Token Index: 636

Text #7

Max Range: 7.7182. Min Range: -7.7182

Max Act: 7.5619. Min Act: -0.1700

Data Index: 696048 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 7.7182. Min Range: -7.7182

Max Act: 7.5932. Min Act: -0.1700

Data Index: 491926 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 7.7182. Min Range: -7.7182

Max Act: 7.4057. Min Act: -0.1700

Data Index: 1090681 (C4 (Web Text))

Max Activating Token Index: 289

Text #10

Max Range: 7.7182. Min Range: -7.7182

Max Act: 7.4369. Min Act: -0.1700

Data Index: 240808 (C4 (Web Text))

Max Activating Token Index: 274

Text #11

Max Range: 7.7182. Min Range: -7.7182

Max Act: 7.6244. Min Act: -0.1700

Data Index: 382435 (C4 (Web Text))

Max Activating Token Index: 261

Text #12

Max Range: 7.7182. Min Range: -7.7182

Max Act: 7.6557. Min Act: -0.1700

Data Index: 463039 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 7.7182. Min Range: -7.7182

Max Act: 7.5307. Min Act: -0.1700

Data Index: 1317931 (C4 (Web Text))

Max Activating Token Index: 238

Text #14

Max Range: 7.7182. Min Range: -7.7182

Max Act: 7.5307. Min Act: -0.1700

Data Index: 1188939 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 7.7182. Min Range: -7.7182

Max Act: 7.4057. Min Act: -0.1700

Data Index: 1119733 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 7.7182. Min Range: -7.7182

Max Act: 7.5307. Min Act: -0.1700

Data Index: 741747 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 7.7182. Min Range: -7.7182

Max Act: 7.4057. Min Act: -0.1700

Data Index: 115437 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 7.7182. Min Range: -7.7182

Max Act: 7.4369. Min Act: -0.1700

Data Index: 1220778 (C4 (Web Text))

Max Activating Token Index: 309

Text #19

Max Range: 7.7182. Min Range: -7.7182

Max Act: 7.4057. Min Act: -0.1700

Data Index: 908934 (C4 (Web Text))

Max Activating Token Index: 548