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

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

Neuron 1438 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: 3.6875. Min Range: -3.6875

Max Act: 3.6875. Min Act: -0.1700

Data Index: 194783 (C4 (Web Text))

Max Activating Token Index: 229

Text #1

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.6562. Min Act: -0.1700

Data Index: 797565 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.5936. Min Act: -0.1700

Data Index: 341225 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.5779. Min Act: -0.1700

Data Index: 341931 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.5310. Min Act: -0.1700

Data Index: 1260943 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.5310. Min Act: -0.1700

Data Index: 1341318 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.4840. Min Act: -0.1700

Data Index: 453346 (C4 (Web Text))

Max Activating Token Index: 843

Text #7

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.4840. Min Act: -0.1700

Data Index: 722433 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.4840. Min Act: -0.1700

Data Index: 440293 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.4526. Min Act: -0.1700

Data Index: 1294491 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.4526. Min Act: -0.1700

Data Index: 856197 (C4 (Web Text))

Max Activating Token Index: 149

Text #11

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.4526. Min Act: -0.1700

Data Index: 925885 (C4 (Web Text))

Max Activating Token Index: 494

Text #12

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.4369. Min Act: -0.1700

Data Index: 922661 (C4 (Web Text))

Max Activating Token Index: 399

Text #13

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.4056. Min Act: -0.1700

Data Index: 49268 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.4056. Min Act: -0.1700

Data Index: 306865 (C4 (Web Text))

Max Activating Token Index: 273

Text #15

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.4213. Min Act: -0.1700

Data Index: 777357 (C4 (Web Text))

Max Activating Token Index: 569

Text #16

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.4213. Min Act: -0.1700

Data Index: 432296 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.3899. Min Act: -0.1700

Data Index: 1278736 (C4 (Web Text))

Max Activating Token Index: 468

Text #18

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.4056. Min Act: -0.1700

Data Index: 55202 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 3.6875. Min Range: -3.6875

Max Act: 3.3899. Min Act: -0.1700

Data Index: 518246 (C4 (Web Text))

Max Activating Token Index: 442