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

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

Neuron 1282 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.8464. Min Act: -0.1700

Data Index: 779220 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.7838. Min Act: -0.1700

Data Index: 1326716 (C4 (Web Text))

Max Activating Token Index: 412

Text #2

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.7525. Min Act: -0.1699

Data Index: 892723 (C4 (Web Text))

Max Activating Token Index: 385

Text #3

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.7838. Min Act: -0.1700

Data Index: 547800 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.6900. Min Act: -0.1700

Data Index: 946600 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.7212. Min Act: -0.1700

Data Index: 1020319 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.6587. Min Act: -0.1700

Data Index: 293588 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.6273. Min Act: -0.1700

Data Index: 466205 (C4 (Web Text))

Max Activating Token Index: 672

Text #8

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.6587. Min Act: -0.1700

Data Index: 795725 (C4 (Web Text))

Max Activating Token Index: 525

Text #9

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.6587. Min Act: -0.1700

Data Index: 687750 (C4 (Web Text))

Max Activating Token Index: 372

Text #10

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.6273. Min Act: -0.1700

Data Index: 339923 (C4 (Web Text))

Max Activating Token Index: 776

Text #11

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.5960. Min Act: -0.1700

Data Index: 479340 (C4 (Web Text))

Max Activating Token Index: 802

Text #12

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.5960. Min Act: -0.1700

Data Index: 1312907 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.5960. Min Act: -0.1700

Data Index: 1121527 (C4 (Web Text))

Max Activating Token Index: 892

Text #14

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.5960. Min Act: -0.1700

Data Index: 400840 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.5334. Min Act: -0.1700

Data Index: 760135 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.5647. Min Act: -0.1700

Data Index: 38487 (C4 (Web Text))

Max Activating Token Index: 652

Text #17

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.5960. Min Act: -0.1700

Data Index: 496299 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.5647. Min Act: -0.1700

Data Index: 143359 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 3.8464. Min Range: -3.8464

Max Act: 3.5647. Min Act: -0.1700

Data Index: 266996 (C4 (Web Text))

Max Activating Token Index: 313