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

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

Neuron 1583 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: 4.1105. Min Range: -4.1105

Max Act: 4.1105. Min Act: -0.1700

Data Index: 88253 (C4 (Web Text))

Max Activating Token Index: 822

Text #1

Max Range: 4.1105. Min Range: -4.1105

Max Act: 4.0168. Min Act: -0.1700

Data Index: 588862 (C4 (Web Text))

Max Activating Token Index: 864

Text #2

Max Range: 4.1105. Min Range: -4.1105

Max Act: 4.0168. Min Act: -0.1700

Data Index: 1145589 (C4 (Web Text))

Max Activating Token Index: 711

Text #3

Max Range: 4.1105. Min Range: -4.1105

Max Act: 4.0168. Min Act: -0.1700

Data Index: 1249659 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 4.1105. Min Range: -4.1105

Max Act: 4.0168. Min Act: -0.1700

Data Index: 509302 (C4 (Web Text))

Max Activating Token Index: 251

Text #5

Max Range: 4.1105. Min Range: -4.1105

Max Act: 4.0168. Min Act: -0.1700

Data Index: 1060704 (C4 (Web Text))

Max Activating Token Index: 361

Text #6

Max Range: 4.1105. Min Range: -4.1105

Max Act: 3.9855. Min Act: -0.1700

Data Index: 813051 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 4.1105. Min Range: -4.1105

Max Act: 3.9855. Min Act: -0.1700

Data Index: 1031902 (C4 (Web Text))

Max Activating Token Index: 110

Text #8

Max Range: 4.1105. Min Range: -4.1105

Max Act: 3.9229. Min Act: -0.1700

Data Index: 956098 (C4 (Web Text))

Max Activating Token Index: 888

Text #9

Max Range: 4.1105. Min Range: -4.1105

Max Act: 3.8917. Min Act: -0.1700

Data Index: 1030074 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 4.1105. Min Range: -4.1105

Max Act: 3.9229. Min Act: -0.1700

Data Index: 561994 (C4 (Web Text))

Max Activating Token Index: 498

Text #11

Max Range: 4.1105. Min Range: -4.1105

Max Act: 3.9229. Min Act: -0.1700

Data Index: 957953 (C4 (Web Text))

Max Activating Token Index: 543

Text #12

Max Range: 4.1105. Min Range: -4.1105

Max Act: 3.8917. Min Act: -0.1700

Data Index: 194594 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 4.1105. Min Range: -4.1105

Max Act: 3.9229. Min Act: -0.1700

Data Index: 175422 (C4 (Web Text))

Max Activating Token Index: 613

Text #14

Max Range: 4.1105. Min Range: -4.1105

Max Act: 3.8604. Min Act: -0.1700

Data Index: 367057 (C4 (Web Text))

Max Activating Token Index: 628

Text #15

Max Range: 4.1105. Min Range: -4.1105

Max Act: 3.8604. Min Act: -0.1700

Data Index: 199565 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 4.1105. Min Range: -4.1105

Max Act: 3.8917. Min Act: -0.1700

Data Index: 986819 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 4.1105. Min Range: -4.1105

Max Act: 3.8604. Min Act: -0.1700

Data Index: 19326 (C4 (Web Text))

Max Activating Token Index: 519

Text #18

Max Range: 4.1105. Min Range: -4.1105

Max Act: 3.8291. Min Act: -0.1700

Data Index: 474441 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 4.1105. Min Range: -4.1105

Max Act: 3.8604. Min Act: -0.1700

Data Index: 12543 (C4 (Web Text))

Max Activating Token Index: 280