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

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

Neuron 344 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: 5.5631. Min Range: -5.5631

Max Act: 5.5631. Min Act: -0.1700

Data Index: 722994 (C4 (Web Text))

Max Activating Token Index: 672

Text #1

Max Range: 5.5631. Min Range: -5.5631

Max Act: 5.3756. Min Act: -0.1700

Data Index: 606851 (C4 (Web Text))

Max Activating Token Index: 337

Text #2

Max Range: 5.5631. Min Range: -5.5631

Max Act: 5.3444. Min Act: -0.1700

Data Index: 452232 (C4 (Web Text))

Max Activating Token Index: 571

Text #3

Max Range: 5.5631. Min Range: -5.5631

Max Act: 5.2194. Min Act: -0.1700

Data Index: 323095 (C4 (Web Text))

Max Activating Token Index: 193

Text #4

Max Range: 5.5631. Min Range: -5.5631

Max Act: 5.2506. Min Act: -0.1700

Data Index: 517280 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 5.5631. Min Range: -5.5631

Max Act: 5.1569. Min Act: -0.1700

Data Index: 1068636 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 5.5631. Min Range: -5.5631

Max Act: 5.0319. Min Act: -0.1700

Data Index: 1037083 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 5.5631. Min Range: -5.5631

Max Act: 5.0006. Min Act: -0.1700

Data Index: 1327108 (C4 (Web Text))

Max Activating Token Index: 461

Text #8

Max Range: 5.5631. Min Range: -5.5631

Max Act: 5.0319. Min Act: -0.1700

Data Index: 307071 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 5.5631. Min Range: -5.5631

Max Act: 5.0319. Min Act: -0.1700

Data Index: 310077 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 5.5631. Min Range: -5.5631

Max Act: 5.0319. Min Act: -0.1700

Data Index: 282225 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 5.5631. Min Range: -5.5631

Max Act: 4.9694. Min Act: -0.1700

Data Index: 928899 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 5.5631. Min Range: -5.5631

Max Act: 4.9694. Min Act: -0.1700

Data Index: 1031124 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 5.5631. Min Range: -5.5631

Max Act: 4.9694. Min Act: -0.1700

Data Index: 884769 (C4 (Web Text))

Max Activating Token Index: 921

Text #14

Max Range: 5.5631. Min Range: -5.5631

Max Act: 4.9694. Min Act: -0.1700

Data Index: 561731 (C4 (Web Text))

Max Activating Token Index: 756

Text #15

Max Range: 5.5631. Min Range: -5.5631

Max Act: 5.0006. Min Act: -0.1700

Data Index: 788117 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 5.5631. Min Range: -5.5631

Max Act: 4.9069. Min Act: -0.1700

Data Index: 192232 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 5.5631. Min Range: -5.5631

Max Act: 4.9381. Min Act: -0.1700

Data Index: 1133200 (C4 (Web Text))

Max Activating Token Index: 336

Text #18

Max Range: 5.5631. Min Range: -5.5631

Max Act: 4.9069. Min Act: -0.1700

Data Index: 1152682 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 5.5631. Min Range: -5.5631

Max Act: 4.9694. Min Act: -0.1700

Data Index: 117474 (C4 (Web Text))

Max Activating Token Index: 435