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

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

Neuron 81 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3347. Min Range: -3.3347

Max Act: 3.3347. Min Act: -0.1700

Data Index: 1102648 (C4 (Web Text))

Max Activating Token Index: 468

Text #1

Max Range: 3.3347. Min Range: -3.3347

Max Act: 3.2248. Min Act: -0.1700

Data Index: 863830 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 3.3347. Min Range: -3.3347

Max Act: 3.0988. Min Act: -0.1700

Data Index: 1242922 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 3.3347. Min Range: -3.3347

Max Act: 3.0988. Min Act: -0.1700

Data Index: 346989 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 3.3347. Min Range: -3.3347

Max Act: 3.0830. Min Act: -0.1700

Data Index: 1304698 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 3.3347. Min Range: -3.3347

Max Act: 3.0672. Min Act: -0.1700

Data Index: 200665 (C4 (Web Text))

Max Activating Token Index: 87

Text #6

Max Range: 3.3347. Min Range: -3.3347

Max Act: 3.0830. Min Act: -0.1700

Data Index: 5078 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 3.3347. Min Range: -3.3347

Max Act: 3.0515. Min Act: -0.1700

Data Index: 1127756 (C4 (Web Text))

Max Activating Token Index: 585

Text #8

Max Range: 3.3347. Min Range: -3.3347

Max Act: 3.0672. Min Act: -0.1700

Data Index: 515419 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 3.3347. Min Range: -3.3347

Max Act: 3.0199. Min Act: -0.1700

Data Index: 1066147 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 3.3347. Min Range: -3.3347

Max Act: 3.0357. Min Act: -0.1700

Data Index: 1263600 (C4 (Web Text))

Max Activating Token Index: 894

Text #11

Max Range: 3.3347. Min Range: -3.3347

Max Act: 3.0041. Min Act: -0.1700

Data Index: 1356845 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 3.3347. Min Range: -3.3347

Max Act: 2.9724. Min Act: -0.1700

Data Index: 927020 (C4 (Web Text))

Max Activating Token Index: 509

Text #13

Max Range: 3.3347. Min Range: -3.3347

Max Act: 2.9408. Min Act: -0.1700

Data Index: 266864 (C4 (Web Text))

Max Activating Token Index: 704

Text #14

Max Range: 3.3347. Min Range: -3.3347

Max Act: 2.9566. Min Act: -0.1700

Data Index: 540734 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 3.3347. Min Range: -3.3347

Max Act: 2.9566. Min Act: -0.1700

Data Index: 3080 (C4 (Web Text))

Max Activating Token Index: 234

Text #16

Max Range: 3.3347. Min Range: -3.3347

Max Act: 2.9408. Min Act: -0.1700

Data Index: 202015 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 3.3347. Min Range: -3.3347

Max Act: 2.9249. Min Act: -0.1700

Data Index: 775963 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 3.3347. Min Range: -3.3347

Max Act: 2.9091. Min Act: -0.1700

Data Index: 677802 (C4 (Web Text))

Max Activating Token Index: 847

Text #19

Max Range: 3.3347. Min Range: -3.3347

Max Act: 2.9249. Min Act: -0.1700

Data Index: 27049 (C4 (Web Text))

Max Activating Token Index: 223