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

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

Neuron 1372 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: 8.4422. Min Range: -8.4422

Max Act: 8.4109. Min Act: -0.1700

Data Index: 1140662 (C4 (Web Text))

Max Activating Token Index: 466

Text #1

Max Range: 8.4422. Min Range: -8.4422

Max Act: 8.3797. Min Act: -0.1700

Data Index: 83420 (C4 (Web Text))

Max Activating Token Index: 339

Text #2

Max Range: 8.4422. Min Range: -8.4422

Max Act: 8.4422. Min Act: -0.1700

Data Index: 1322994 (C4 (Web Text))

Max Activating Token Index: 367

Text #3

Max Range: 8.4422. Min Range: -8.4422

Max Act: 8.4422. Min Act: -0.1700

Data Index: 467698 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 8.4422. Min Range: -8.4422

Max Act: 8.2859. Min Act: -0.1700

Data Index: 963237 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 8.4422. Min Range: -8.4422

Max Act: 8.3172. Min Act: -0.1700

Data Index: 779858 (C4 (Web Text))

Max Activating Token Index: 195

Text #6

Max Range: 8.4422. Min Range: -8.4422

Max Act: 8.3484. Min Act: -0.1700

Data Index: 1208915 (C4 (Web Text))

Max Activating Token Index: 417

Text #7

Max Range: 8.4422. Min Range: -8.4422

Max Act: 8.2547. Min Act: -0.1700

Data Index: 52193 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 8.4422. Min Range: -8.4422

Max Act: 8.2859. Min Act: -0.1700

Data Index: 200818 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 8.4422. Min Range: -8.4422

Max Act: 8.1922. Min Act: -0.1700

Data Index: 870032 (C4 (Web Text))

Max Activating Token Index: 437

Text #10

Max Range: 8.4422. Min Range: -8.4422

Max Act: 8.2234. Min Act: -0.1700

Data Index: 658190 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 8.4422. Min Range: -8.4422

Max Act: 8.2547. Min Act: -0.1700

Data Index: 344253 (C4 (Web Text))

Max Activating Token Index: 237

Text #12

Max Range: 8.4422. Min Range: -8.4422

Max Act: 8.1609. Min Act: -0.1700

Data Index: 390516 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 8.4422. Min Range: -8.4422

Max Act: 8.1922. Min Act: -0.1700

Data Index: 384840 (C4 (Web Text))

Max Activating Token Index: 826

Text #14

Max Range: 8.4422. Min Range: -8.4422

Max Act: 8.1609. Min Act: -0.1700

Data Index: 308935 (C4 (Web Text))

Max Activating Token Index: 341

Text #15

Max Range: 8.4422. Min Range: -8.4422

Max Act: 8.1297. Min Act: -0.1700

Data Index: 397596 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 8.4422. Min Range: -8.4422

Max Act: 8.1922. Min Act: -0.1700

Data Index: 20935 (C4 (Web Text))

Max Activating Token Index: 269

Text #17

Max Range: 8.4422. Min Range: -8.4422

Max Act: 8.1297. Min Act: -0.1700

Data Index: 389606 (C4 (Web Text))

Max Activating Token Index: 156

Text #18

Max Range: 8.4422. Min Range: -8.4422

Max Act: 8.0672. Min Act: -0.1700

Data Index: 523588 (C4 (Web Text))

Max Activating Token Index: 747

Text #19

Max Range: 8.4422. Min Range: -8.4422

Max Act: 8.1609. Min Act: -0.1700

Data Index: 66064 (C4 (Web Text))

Max Activating Token Index: 281