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

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

Neuron 1732 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: 5.4846. Min Range: -5.4846

Max Act: 5.4846. Min Act: -0.1700

Data Index: 253246 (C4 (Web Text))

Max Activating Token Index: 317

Text #1

Max Range: 5.4846. Min Range: -5.4846

Max Act: 5.3909. Min Act: -0.1700

Data Index: 133593 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 5.4846. Min Range: -5.4846

Max Act: 5.4221. Min Act: -0.1700

Data Index: 293166 (C4 (Web Text))

Max Activating Token Index: 293

Text #3

Max Range: 5.4846. Min Range: -5.4846

Max Act: 5.3909. Min Act: -0.1700

Data Index: 16561 (C4 (Web Text))

Max Activating Token Index: 291

Text #4

Max Range: 5.4846. Min Range: -5.4846

Max Act: 5.3909. Min Act: -0.1700

Data Index: 941053 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 5.4846. Min Range: -5.4846

Max Act: 5.4534. Min Act: -0.1700

Data Index: 291232 (C4 (Web Text))

Max Activating Token Index: 497

Text #6

Max Range: 5.4846. Min Range: -5.4846

Max Act: 5.3909. Min Act: -0.1700

Data Index: 487181 (C4 (Web Text))

Max Activating Token Index: 382

Text #7

Max Range: 5.4846. Min Range: -5.4846

Max Act: 5.3596. Min Act: -0.1700

Data Index: 727916 (C4 (Web Text))

Max Activating Token Index: 521

Text #8

Max Range: 5.4846. Min Range: -5.4846

Max Act: 5.3284. Min Act: -0.1700

Data Index: 727620 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 5.4846. Min Range: -5.4846

Max Act: 5.2659. Min Act: -0.1700

Data Index: 753396 (C4 (Web Text))

Max Activating Token Index: 680

Text #10

Max Range: 5.4846. Min Range: -5.4846

Max Act: 5.3596. Min Act: -0.1700

Data Index: 1081542 (C4 (Web Text))

Max Activating Token Index: 475

Text #11

Max Range: 5.4846. Min Range: -5.4846

Max Act: 5.3284. Min Act: -0.1700

Data Index: 1207719 (C4 (Web Text))

Max Activating Token Index: 760

Text #12

Max Range: 5.4846. Min Range: -5.4846

Max Act: 5.2659. Min Act: -0.1700

Data Index: 428410 (C4 (Web Text))

Max Activating Token Index: 854

Text #13

Max Range: 5.4846. Min Range: -5.4846

Max Act: 5.2034. Min Act: -0.1700

Data Index: 8654 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 5.4846. Min Range: -5.4846

Max Act: 5.3284. Min Act: -0.1700

Data Index: 367994 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 5.4846. Min Range: -5.4846

Max Act: 5.3596. Min Act: -0.1700

Data Index: 1197198 (C4 (Web Text))

Max Activating Token Index: 375

Text #16

Max Range: 5.4846. Min Range: -5.4846

Max Act: 5.3596. Min Act: -0.1700

Data Index: 1140207 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 5.4846. Min Range: -5.4846

Max Act: 5.2659. Min Act: -0.1700

Data Index: 287917 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 5.4846. Min Range: -5.4846

Max Act: 5.3284. Min Act: -0.1700

Data Index: 615481 (C4 (Web Text))

Max Activating Token Index: 871

Text #19

Max Range: 5.4846. Min Range: -5.4846

Max Act: 5.2034. Min Act: -0.1700

Data Index: 1220313 (C4 (Web Text))

Max Activating Token Index: 585