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

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

Neuron 1995 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.3506. Min Range: -3.3506

Max Act: 3.3506. Min Act: -0.1700

Data Index: 1220264 (C4 (Web Text))

Max Activating Token Index: 825

Text #1

Max Range: 3.3506. Min Range: -3.3506

Max Act: 3.3192. Min Act: -0.1700

Data Index: 848063 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 3.3506. Min Range: -3.3506

Max Act: 3.3192. Min Act: -0.1700

Data Index: 786159 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 3.3506. Min Range: -3.3506

Max Act: 3.2564. Min Act: -0.1700

Data Index: 739311 (C4 (Web Text))

Max Activating Token Index: 485

Text #4

Max Range: 3.3506. Min Range: -3.3506

Max Act: 3.2564. Min Act: -0.1700

Data Index: 630325 (C4 (Web Text))

Max Activating Token Index: 801

Text #5

Max Range: 3.3506. Min Range: -3.3506

Max Act: 3.2564. Min Act: -0.1700

Data Index: 181466 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 3.3506. Min Range: -3.3506

Max Act: 3.2564. Min Act: -0.1700

Data Index: 1030941 (C4 (Web Text))

Max Activating Token Index: 520

Text #7

Max Range: 3.3506. Min Range: -3.3506

Max Act: 3.2564. Min Act: -0.1700

Data Index: 397422 (C4 (Web Text))

Max Activating Token Index: 529

Text #8

Max Range: 3.3506. Min Range: -3.3506

Max Act: 3.2564. Min Act: -0.1700

Data Index: 603539 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 3.3506. Min Range: -3.3506

Max Act: 3.2564. Min Act: -0.1700

Data Index: 563818 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 3.3506. Min Range: -3.3506

Max Act: 3.2564. Min Act: -0.1700

Data Index: 1250114 (C4 (Web Text))

Max Activating Token Index: 791

Text #11

Max Range: 3.3506. Min Range: -3.3506

Max Act: 3.2249. Min Act: -0.1700

Data Index: 265884 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 3.3506. Min Range: -3.3506

Max Act: 3.2564. Min Act: -0.1700

Data Index: 53796 (C4 (Web Text))

Max Activating Token Index: 374

Text #13

Max Range: 3.3506. Min Range: -3.3506

Max Act: 3.2092. Min Act: -0.1700

Data Index: 1245239 (C4 (Web Text))

Max Activating Token Index: 962

Text #14

Max Range: 3.3506. Min Range: -3.3506

Max Act: 3.2564. Min Act: -0.1700

Data Index: 1234495 (C4 (Web Text))

Max Activating Token Index: 264

Text #15

Max Range: 3.3506. Min Range: -3.3506

Max Act: 3.2092. Min Act: -0.1700

Data Index: 607608 (C4 (Web Text))

Max Activating Token Index: 165

Text #16

Max Range: 3.3506. Min Range: -3.3506

Max Act: 3.2407. Min Act: -0.1700

Data Index: 1109315 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 3.3506. Min Range: -3.3506

Max Act: 3.2249. Min Act: -0.1700

Data Index: 4373 (C4 (Web Text))

Max Activating Token Index: 625

Text #18

Max Range: 3.3506. Min Range: -3.3506

Max Act: 3.1147. Min Act: -0.1700

Data Index: 14525 (C4 (Web Text))

Max Activating Token Index: 580

Text #19

Max Range: 3.3506. Min Range: -3.3506

Max Act: 3.1620. Min Act: -0.1700

Data Index: 832332 (C4 (Web Text))

Max Activating Token Index: 949