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

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

Neuron 1947 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: 5.6473. Min Range: -5.6473

Max Act: 5.6473. Min Act: -0.1699

Data Index: 1301972 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 5.6473. Min Range: -5.6473

Max Act: 5.4286. Min Act: -0.1700

Data Index: 705894 (C4 (Web Text))

Max Activating Token Index: 712

Text #2

Max Range: 5.6473. Min Range: -5.6473

Max Act: 5.3661. Min Act: -0.1700

Data Index: 14251 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 5.6473. Min Range: -5.6473

Max Act: 5.3661. Min Act: -0.1699

Data Index: 193208 (C4 (Web Text))

Max Activating Token Index: 979

Text #4

Max Range: 5.6473. Min Range: -5.6473

Max Act: 5.3348. Min Act: -0.1700

Data Index: 319281 (C4 (Web Text))

Max Activating Token Index: 971

Text #5

Max Range: 5.6473. Min Range: -5.6473

Max Act: 5.2411. Min Act: -0.1699

Data Index: 479075 (C4 (Web Text))

Max Activating Token Index: 916

Text #6

Max Range: 5.6473. Min Range: -5.6473

Max Act: 5.2723. Min Act: -0.1697

Data Index: 233395 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 5.6473. Min Range: -5.6473

Max Act: 5.3036. Min Act: -0.1698

Data Index: 1087128 (C4 (Web Text))

Max Activating Token Index: 704

Text #8

Max Range: 5.6473. Min Range: -5.6473

Max Act: 5.2723. Min Act: -0.1700

Data Index: 278778 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 5.6473. Min Range: -5.6473

Max Act: 5.3036. Min Act: -0.1700

Data Index: 1130335 (C4 (Web Text))

Max Activating Token Index: 632

Text #10

Max Range: 5.6473. Min Range: -5.6473

Max Act: 5.2723. Min Act: -0.1697

Data Index: 824652 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 5.6473. Min Range: -5.6473

Max Act: 5.2411. Min Act: -0.1700

Data Index: 179325 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 5.6473. Min Range: -5.6473

Max Act: 5.2723. Min Act: -0.1700

Data Index: 582950 (C4 (Web Text))

Max Activating Token Index: 965

Text #13

Max Range: 5.6473. Min Range: -5.6473

Max Act: 5.2411. Min Act: -0.1700

Data Index: 688275 (C4 (Web Text))

Max Activating Token Index: 335

Text #14

Max Range: 5.6473. Min Range: -5.6473

Max Act: 5.2098. Min Act: -0.1699

Data Index: 1012994 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 5.6473. Min Range: -5.6473

Max Act: 5.2411. Min Act: -0.1700

Data Index: 785784 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 5.6473. Min Range: -5.6473

Max Act: 5.2098. Min Act: -0.1699

Data Index: 957476 (C4 (Web Text))

Max Activating Token Index: 712

Text #17

Max Range: 5.6473. Min Range: -5.6473

Max Act: 5.2723. Min Act: -0.1700

Data Index: 1286963 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 5.6473. Min Range: -5.6473

Max Act: 5.2411. Min Act: -0.1700

Data Index: 106554 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 5.6473. Min Range: -5.6473

Max Act: 5.1786. Min Act: -0.1700

Data Index: 880077 (C4 (Web Text))

Max Activating Token Index: 157