Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1950 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.4860. Min Range: -3.4860

Max Act: 3.4860. Min Act: -0.1700

Data Index: 1283505 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 3.4860. Min Range: -3.4860

Max Act: 3.4860. Min Act: -0.1700

Data Index: 654087 (C4 (Web Text))

Max Activating Token Index: 149

Text #2

Max Range: 3.4860. Min Range: -3.4860

Max Act: 3.4547. Min Act: -0.1700

Data Index: 356636 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 3.4860. Min Range: -3.4860

Max Act: 3.4704. Min Act: -0.1700

Data Index: 892113 (C4 (Web Text))

Max Activating Token Index: 724

Text #4

Max Range: 3.4860. Min Range: -3.4860

Max Act: 3.3292. Min Act: -0.1700

Data Index: 1042165 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 3.4860. Min Range: -3.4860

Max Act: 3.2821. Min Act: -0.1700

Data Index: 171275 (C4 (Web Text))

Max Activating Token Index: 393

Text #6

Max Range: 3.4860. Min Range: -3.4860

Max Act: 3.2821. Min Act: -0.1700

Data Index: 385471 (C4 (Web Text))

Max Activating Token Index: 187

Text #7

Max Range: 3.4860. Min Range: -3.4860

Max Act: 3.2664. Min Act: -0.1700

Data Index: 814622 (C4 (Web Text))

Max Activating Token Index: 506

Text #8

Max Range: 3.4860. Min Range: -3.4860

Max Act: 3.2664. Min Act: -0.1700

Data Index: 1005106 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 3.4860. Min Range: -3.4860

Max Act: 3.2506. Min Act: -0.1700

Data Index: 893438 (C4 (Web Text))

Max Activating Token Index: 382

Text #10

Max Range: 3.4860. Min Range: -3.4860

Max Act: 3.2664. Min Act: -0.1700

Data Index: 461391 (C4 (Web Text))

Max Activating Token Index: 24

Text #11

Max Range: 3.4860. Min Range: -3.4860

Max Act: 3.2349. Min Act: -0.1700

Data Index: 1017562 (C4 (Web Text))

Max Activating Token Index: 218

Text #12

Max Range: 3.4860. Min Range: -3.4860

Max Act: 3.2664. Min Act: -0.1700

Data Index: 1219352 (C4 (Web Text))

Max Activating Token Index: 2

Text #13

Max Range: 3.4860. Min Range: -3.4860

Max Act: 3.2192. Min Act: -0.1700

Data Index: 1349321 (C4 (Web Text))

Max Activating Token Index: 322

Text #14

Max Range: 3.4860. Min Range: -3.4860

Max Act: 3.2192. Min Act: -0.1700

Data Index: 84145 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 3.4860. Min Range: -3.4860

Max Act: 3.2349. Min Act: -0.1700

Data Index: 475139 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 3.4860. Min Range: -3.4860

Max Act: 3.2349. Min Act: -0.1700

Data Index: 656053 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 3.4860. Min Range: -3.4860

Max Act: 3.2349. Min Act: -0.1700

Data Index: 1133462 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 3.4860. Min Range: -3.4860

Max Act: 3.2349. Min Act: -0.1700

Data Index: 658382 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 3.4860. Min Range: -3.4860

Max Act: 3.2192. Min Act: -0.1700

Data Index: 1154310 (C4 (Web Text))

Max Activating Token Index: 346