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

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

Neuron 1944 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: 3.6434. Min Range: -3.6434

Max Act: 3.6277. Min Act: -0.1700

Data Index: 174479 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 3.6434. Min Range: -3.6434

Max Act: 3.6277. Min Act: -0.1700

Data Index: 120308 (C4 (Web Text))

Max Activating Token Index: 109

Text #2

Max Range: 3.6434. Min Range: -3.6434

Max Act: 3.6277. Min Act: -0.1700

Data Index: 1286016 (C4 (Web Text))

Max Activating Token Index: 559

Text #3

Max Range: 3.6434. Min Range: -3.6434

Max Act: 3.6434. Min Act: -0.1700

Data Index: 545025 (C4 (Web Text))

Max Activating Token Index: 341

Text #4

Max Range: 3.6434. Min Range: -3.6434

Max Act: 3.6277. Min Act: -0.1700

Data Index: 400766 (C4 (Web Text))

Max Activating Token Index: 270

Text #5

Max Range: 3.6434. Min Range: -3.6434

Max Act: 3.6121. Min Act: -0.1700

Data Index: 912061 (C4 (Web Text))

Max Activating Token Index: 594

Text #6

Max Range: 3.6434. Min Range: -3.6434

Max Act: 3.5808. Min Act: -0.1700

Data Index: 782966 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 3.6434. Min Range: -3.6434

Max Act: 3.5964. Min Act: -0.1700

Data Index: 1238484 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 3.6434. Min Range: -3.6434

Max Act: 3.5808. Min Act: -0.1700

Data Index: 554332 (C4 (Web Text))

Max Activating Token Index: 1005

Text #9

Max Range: 3.6434. Min Range: -3.6434

Max Act: 3.5338. Min Act: -0.1700

Data Index: 498140 (C4 (Web Text))

Max Activating Token Index: 459

Text #10

Max Range: 3.6434. Min Range: -3.6434

Max Act: 3.5651. Min Act: -0.1700

Data Index: 327506 (C4 (Web Text))

Max Activating Token Index: 544

Text #11

Max Range: 3.6434. Min Range: -3.6434

Max Act: 3.5651. Min Act: -0.1700

Data Index: 602134 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 3.6434. Min Range: -3.6434

Max Act: 3.5651. Min Act: -0.1700

Data Index: 1313860 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 3.6434. Min Range: -3.6434

Max Act: 3.5651. Min Act: -0.1700

Data Index: 181686 (C4 (Web Text))

Max Activating Token Index: 1001

Text #14

Max Range: 3.6434. Min Range: -3.6434

Max Act: 3.5181. Min Act: -0.1700

Data Index: 361701 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 3.6434. Min Range: -3.6434

Max Act: 3.4868. Min Act: -0.1700

Data Index: 958749 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 3.6434. Min Range: -3.6434

Max Act: 3.5025. Min Act: -0.1700

Data Index: 893770 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 3.6434. Min Range: -3.6434

Max Act: 3.5338. Min Act: -0.1700

Data Index: 924605 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 3.6434. Min Range: -3.6434

Max Act: 3.5025. Min Act: -0.1700

Data Index: 875226 (C4 (Web Text))

Max Activating Token Index: 768

Text #19

Max Range: 3.6434. Min Range: -3.6434

Max Act: 3.5338. Min Act: -0.1700

Data Index: 139227 (C4 (Web Text))

Max Activating Token Index: 308