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

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

Neuron 1613 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.5280. Min Act: -0.1700

Data Index: 895904 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.5280. Min Act: -0.1700

Data Index: 341539 (C4 (Web Text))

Max Activating Token Index: 437

Text #2

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.4967. Min Act: -0.1700

Data Index: 118589 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.4967. Min Act: -0.1700

Data Index: 1219460 (C4 (Web Text))

Max Activating Token Index: 232

Text #4

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.4653. Min Act: -0.1700

Data Index: 720079 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.4183. Min Act: -0.1700

Data Index: 184548 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.4026. Min Act: -0.1700

Data Index: 496964 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.3869. Min Act: -0.1700

Data Index: 347775 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.3713. Min Act: -0.1700

Data Index: 933451 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.3713. Min Act: -0.1700

Data Index: 443740 (C4 (Web Text))

Max Activating Token Index: 803

Text #10

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.3556. Min Act: -0.1700

Data Index: 1058905 (C4 (Web Text))

Max Activating Token Index: 844

Text #11

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.3399. Min Act: -0.1700

Data Index: 374026 (C4 (Web Text))

Max Activating Token Index: 924

Text #12

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.3085. Min Act: -0.1700

Data Index: 1245254 (C4 (Web Text))

Max Activating Token Index: 200

Text #13

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.3085. Min Act: -0.1700

Data Index: 1069092 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.3399. Min Act: -0.1700

Data Index: 922744 (C4 (Web Text))

Max Activating Token Index: 149

Text #15

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.3242. Min Act: -0.1700

Data Index: 831212 (C4 (Web Text))

Max Activating Token Index: 561

Text #16

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.3242. Min Act: -0.1700

Data Index: 269215 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.3242. Min Act: -0.1700

Data Index: 395679 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.3242. Min Act: -0.1700

Data Index: 912239 (C4 (Web Text))

Max Activating Token Index: 660

Text #19

Max Range: 3.5280. Min Range: -3.5280

Max Act: 3.2928. Min Act: -0.1700

Data Index: 590123 (C4 (Web Text))

Max Activating Token Index: 78