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

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

Neuron 382 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.6839. Min Range: -3.6839

Max Act: 3.6839. Min Act: -0.1700

Data Index: 1209119 (C4 (Web Text))

Max Activating Token Index: 398

Text #1

Max Range: 3.6839. Min Range: -3.6839

Max Act: 3.4646. Min Act: -0.1700

Data Index: 555372 (C4 (Web Text))

Max Activating Token Index: 484

Text #2

Max Range: 3.6839. Min Range: -3.6839

Max Act: 3.4646. Min Act: -0.1700

Data Index: 1291086 (C4 (Web Text))

Max Activating Token Index: 235

Text #3

Max Range: 3.6839. Min Range: -3.6839

Max Act: 3.5273. Min Act: -0.1700

Data Index: 801902 (C4 (Web Text))

Max Activating Token Index: 856

Text #4

Max Range: 3.6839. Min Range: -3.6839

Max Act: 3.4019. Min Act: -0.1700

Data Index: 445617 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 3.6839. Min Range: -3.6839

Max Act: 3.4646. Min Act: -0.1700

Data Index: 940479 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 3.6839. Min Range: -3.6839

Max Act: 3.4960. Min Act: -0.1700

Data Index: 856968 (C4 (Web Text))

Max Activating Token Index: 580

Text #7

Max Range: 3.6839. Min Range: -3.6839

Max Act: 3.4333. Min Act: -0.1700

Data Index: 594402 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 3.6839. Min Range: -3.6839

Max Act: 3.4019. Min Act: -0.1700

Data Index: 146546 (C4 (Web Text))

Max Activating Token Index: 490

Text #9

Max Range: 3.6839. Min Range: -3.6839

Max Act: 3.4333. Min Act: -0.1700

Data Index: 959473 (C4 (Web Text))

Max Activating Token Index: 253

Text #10

Max Range: 3.6839. Min Range: -3.6839

Max Act: 3.4019. Min Act: -0.1700

Data Index: 1273163 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 3.6839. Min Range: -3.6839

Max Act: 3.4019. Min Act: -0.1700

Data Index: 167304 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 3.6839. Min Range: -3.6839

Max Act: 3.4333. Min Act: -0.1700

Data Index: 1029505 (C4 (Web Text))

Max Activating Token Index: 372

Text #13

Max Range: 3.6839. Min Range: -3.6839

Max Act: 3.4019. Min Act: -0.1700

Data Index: 553036 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 3.6839. Min Range: -3.6839

Max Act: 3.4333. Min Act: -0.1700

Data Index: 554701 (C4 (Web Text))

Max Activating Token Index: 137

Text #15

Max Range: 3.6839. Min Range: -3.6839

Max Act: 3.3391. Min Act: -0.1700

Data Index: 12968 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 3.6839. Min Range: -3.6839

Max Act: 3.3705. Min Act: -0.1700

Data Index: 944515 (C4 (Web Text))

Max Activating Token Index: 911

Text #17

Max Range: 3.6839. Min Range: -3.6839

Max Act: 3.3705. Min Act: -0.1700

Data Index: 351865 (C4 (Web Text))

Max Activating Token Index: 494

Text #18

Max Range: 3.6839. Min Range: -3.6839

Max Act: 3.4333. Min Act: -0.1700

Data Index: 766696 (C4 (Web Text))

Max Activating Token Index: 184

Text #19

Max Range: 3.6839. Min Range: -3.6839

Max Act: 3.3391. Min Act: -0.1700

Data Index: 106058 (C4 (Web Text))

Max Activating Token Index: 637