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

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

Neuron 1826 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: 5.3999. Min Range: -5.3999

Max Act: 5.3999. Min Act: -0.1700

Data Index: 1020814 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 5.3999. Min Range: -5.3999

Max Act: 5.3374. Min Act: -0.1700

Data Index: 661067 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 5.3999. Min Range: -5.3999

Max Act: 5.3061. Min Act: -0.1700

Data Index: 751313 (C4 (Web Text))

Max Activating Token Index: 480

Text #3

Max Range: 5.3999. Min Range: -5.3999

Max Act: 5.2124. Min Act: -0.1700

Data Index: 1183025 (C4 (Web Text))

Max Activating Token Index: 395

Text #4

Max Range: 5.3999. Min Range: -5.3999

Max Act: 5.1811. Min Act: -0.1700

Data Index: 138878 (C4 (Web Text))

Max Activating Token Index: 358

Text #5

Max Range: 5.3999. Min Range: -5.3999

Max Act: 5.2436. Min Act: -0.1700

Data Index: 466150 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 5.3999. Min Range: -5.3999

Max Act: 5.2124. Min Act: -0.1700

Data Index: 325198 (C4 (Web Text))

Max Activating Token Index: 147

Text #7

Max Range: 5.3999. Min Range: -5.3999

Max Act: 5.2124. Min Act: -0.1700

Data Index: 1137298 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 5.3999. Min Range: -5.3999

Max Act: 5.2124. Min Act: -0.1700

Data Index: 959567 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 5.3999. Min Range: -5.3999

Max Act: 5.1811. Min Act: -0.1700

Data Index: 376147 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 5.3999. Min Range: -5.3999

Max Act: 5.1186. Min Act: -0.1700

Data Index: 843701 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 5.3999. Min Range: -5.3999

Max Act: 5.0874. Min Act: -0.1700

Data Index: 204772 (C4 (Web Text))

Max Activating Token Index: 860

Text #12

Max Range: 5.3999. Min Range: -5.3999

Max Act: 5.1811. Min Act: -0.1700

Data Index: 1145654 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 5.3999. Min Range: -5.3999

Max Act: 5.1811. Min Act: -0.1700

Data Index: 1219814 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 5.3999. Min Range: -5.3999

Max Act: 5.0874. Min Act: -0.1700

Data Index: 302930 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 5.3999. Min Range: -5.3999

Max Act: 5.0874. Min Act: -0.1700

Data Index: 60030 (C4 (Web Text))

Max Activating Token Index: 491

Text #16

Max Range: 5.3999. Min Range: -5.3999

Max Act: 5.0561. Min Act: -0.1700

Data Index: 926917 (C4 (Web Text))

Max Activating Token Index: 881

Text #17

Max Range: 5.3999. Min Range: -5.3999

Max Act: 5.1186. Min Act: -0.1700

Data Index: 1315221 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 5.3999. Min Range: -5.3999

Max Act: 5.0874. Min Act: -0.1700

Data Index: 361090 (C4 (Web Text))

Max Activating Token Index: 442

Text #19

Max Range: 5.3999. Min Range: -5.3999

Max Act: 5.0561. Min Act: -0.1700

Data Index: 751488 (C4 (Web Text))

Max Activating Token Index: 733