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

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

Neuron 1846 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: 5.3899. Min Range: -5.3899

Max Act: 5.3587. Min Act: -0.1700

Data Index: 1200585 (C4 (Web Text))

Max Activating Token Index: 546

Text #1

Max Range: 5.3899. Min Range: -5.3899

Max Act: 5.3899. Min Act: -0.1700

Data Index: 1246596 (C4 (Web Text))

Max Activating Token Index: 153

Text #2

Max Range: 5.3899. Min Range: -5.3899

Max Act: 5.3274. Min Act: -0.1700

Data Index: 932208 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 5.3899. Min Range: -5.3899

Max Act: 5.2649. Min Act: -0.1700

Data Index: 1093315 (C4 (Web Text))

Max Activating Token Index: 470

Text #4

Max Range: 5.3899. Min Range: -5.3899

Max Act: 5.3274. Min Act: -0.1700

Data Index: 1008676 (C4 (Web Text))

Max Activating Token Index: 514

Text #5

Max Range: 5.3899. Min Range: -5.3899

Max Act: 5.2962. Min Act: -0.1700

Data Index: 895789 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 5.3899. Min Range: -5.3899

Max Act: 5.2337. Min Act: -0.1700

Data Index: 26639 (C4 (Web Text))

Max Activating Token Index: 696

Text #7

Max Range: 5.3899. Min Range: -5.3899

Max Act: 5.2337. Min Act: -0.1700

Data Index: 727188 (C4 (Web Text))

Max Activating Token Index: 281

Text #8

Max Range: 5.3899. Min Range: -5.3899

Max Act: 5.2337. Min Act: -0.1700

Data Index: 407532 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 5.3899. Min Range: -5.3899

Max Act: 5.2337. Min Act: -0.1700

Data Index: 41689 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 5.3899. Min Range: -5.3899

Max Act: 5.2337. Min Act: -0.1700

Data Index: 354636 (C4 (Web Text))

Max Activating Token Index: 379

Text #11

Max Range: 5.3899. Min Range: -5.3899

Max Act: 5.2337. Min Act: -0.1700

Data Index: 1179017 (C4 (Web Text))

Max Activating Token Index: 176

Text #12

Max Range: 5.3899. Min Range: -5.3899

Max Act: 5.1712. Min Act: -0.1700

Data Index: 548604 (C4 (Web Text))

Max Activating Token Index: 332

Text #13

Max Range: 5.3899. Min Range: -5.3899

Max Act: 5.1712. Min Act: -0.1700

Data Index: 1255334 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 5.3899. Min Range: -5.3899

Max Act: 5.1712. Min Act: -0.1700

Data Index: 1080021 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 5.3899. Min Range: -5.3899

Max Act: 5.1712. Min Act: -0.1700

Data Index: 751811 (C4 (Web Text))

Max Activating Token Index: 82

Text #16

Max Range: 5.3899. Min Range: -5.3899

Max Act: 5.2337. Min Act: -0.1700

Data Index: 934391 (C4 (Web Text))

Max Activating Token Index: 25

Text #17

Max Range: 5.3899. Min Range: -5.3899

Max Act: 5.1399. Min Act: -0.1699

Data Index: 974047 (C4 (Web Text))

Max Activating Token Index: 607

Text #18

Max Range: 5.3899. Min Range: -5.3899

Max Act: 5.1399. Min Act: -0.1700

Data Index: 1184406 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 5.3899. Min Range: -5.3899

Max Act: 5.1087. Min Act: -0.1700

Data Index: 452248 (C4 (Web Text))

Max Activating Token Index: 633