Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 466 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 6.3796. Min Range: -6.3796

Max Act: 6.3796. Min Act: -0.1700

Data Index: 1518211 (Python Code)

Max Activating Token Index: 924

Text #1

Max Range: 6.3796. Min Range: -6.3796

Max Act: 6.3171. Min Act: -0.1700

Data Index: 969717 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 6.3796. Min Range: -6.3796

Max Act: 6.2702. Min Act: -0.1700

Data Index: 753216 (C4 (Web Text))

Max Activating Token Index: 1013

Text #3

Max Range: 6.3796. Min Range: -6.3796

Max Act: 6.1296. Min Act: -0.1700

Data Index: 1639661 (Python Code)

Max Activating Token Index: 655

Text #4

Max Range: 6.3796. Min Range: -6.3796

Max Act: 6.2389. Min Act: -0.1700

Data Index: 1252323 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 6.3796. Min Range: -6.3796

Max Act: 6.1296. Min Act: -0.1700

Data Index: 1182938 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 6.3796. Min Range: -6.3796

Max Act: 6.0827. Min Act: -0.1700

Data Index: 1533911 (Python Code)

Max Activating Token Index: 435

Text #7

Max Range: 6.3796. Min Range: -6.3796

Max Act: 6.0983. Min Act: -0.1700

Data Index: 1486529 (Python Code)

Max Activating Token Index: 258

Text #8

Max Range: 6.3796. Min Range: -6.3796

Max Act: 6.0905. Min Act: -0.1700

Data Index: 452144 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 6.3796. Min Range: -6.3796

Max Act: 6.0592. Min Act: -0.1700

Data Index: 1564276 (Python Code)

Max Activating Token Index: 512

Text #10

Max Range: 6.3796. Min Range: -6.3796

Max Act: 6.0671. Min Act: -0.1700

Data Index: 1594381 (Python Code)

Max Activating Token Index: 890

Text #11

Max Range: 6.3796. Min Range: -6.3796

Max Act: 6.0358. Min Act: -0.1700

Data Index: 1653836 (Python Code)

Max Activating Token Index: 406

Text #12

Max Range: 6.3796. Min Range: -6.3796

Max Act: 6.0202. Min Act: -0.1700

Data Index: 309794 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 6.3796. Min Range: -6.3796

Max Act: 6.0202. Min Act: -0.1700

Data Index: 1474782 (Python Code)

Max Activating Token Index: 406

Text #14

Max Range: 6.3796. Min Range: -6.3796

Max Act: 5.9264. Min Act: -0.1700

Data Index: 924738 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 6.3796. Min Range: -6.3796

Max Act: 5.9342. Min Act: -0.1700

Data Index: 2492 (C4 (Web Text))

Max Activating Token Index: 120

Text #16

Max Range: 6.3796. Min Range: -6.3796

Max Act: 5.7780. Min Act: -0.1700

Data Index: 1004793 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 6.3796. Min Range: -6.3796

Max Act: 5.8092. Min Act: -0.1700

Data Index: 1211345 (C4 (Web Text))

Max Activating Token Index: 326

Text #18

Max Range: 6.3796. Min Range: -6.3796

Max Act: 5.8249. Min Act: -0.1700

Data Index: 504880 (C4 (Web Text))

Max Activating Token Index: 205

Text #19

Max Range: 6.3796. Min Range: -6.3796

Max Act: 5.7702. Min Act: -0.1700

Data Index: 1325213 (C4 (Web Text))

Max Activating Token Index: 509