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

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

Neuron 1468 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0655. Min Range: -3.0655

Max Act: 3.0655. Min Act: -0.1700

Data Index: 609033 (C4 (Web Text))

Max Activating Token Index: 124

Text #1

Max Range: 3.0655. Min Range: -3.0655

Max Act: 3.0339. Min Act: -0.1700

Data Index: 450495 (C4 (Web Text))

Max Activating Token Index: 575

Text #2

Max Range: 3.0655. Min Range: -3.0655

Max Act: 3.0339. Min Act: -0.1700

Data Index: 765677 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 3.0655. Min Range: -3.0655

Max Act: 3.0339. Min Act: -0.1700

Data Index: 1133488 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 3.0655. Min Range: -3.0655

Max Act: 3.0339. Min Act: -0.1700

Data Index: 820588 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 3.0655. Min Range: -3.0655

Max Act: 3.0181. Min Act: -0.1700

Data Index: 1298999 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 3.0655. Min Range: -3.0655

Max Act: 3.0023. Min Act: -0.1700

Data Index: 295327 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 3.0655. Min Range: -3.0655

Max Act: 3.0023. Min Act: -0.1700

Data Index: 373987 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 3.0655. Min Range: -3.0655

Max Act: 3.0023. Min Act: -0.1700

Data Index: 311131 (C4 (Web Text))

Max Activating Token Index: 458

Text #9

Max Range: 3.0655. Min Range: -3.0655

Max Act: 2.9865. Min Act: -0.1700

Data Index: 159204 (C4 (Web Text))

Max Activating Token Index: 465

Text #10

Max Range: 3.0655. Min Range: -3.0655

Max Act: 2.9706. Min Act: -0.1700

Data Index: 1163925 (C4 (Web Text))

Max Activating Token Index: 449

Text #11

Max Range: 3.0655. Min Range: -3.0655

Max Act: 2.9706. Min Act: -0.1700

Data Index: 390022 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 3.0655. Min Range: -3.0655

Max Act: 2.9865. Min Act: -0.1700

Data Index: 1126027 (C4 (Web Text))

Max Activating Token Index: 987

Text #13

Max Range: 3.0655. Min Range: -3.0655

Max Act: 2.9706. Min Act: -0.1700

Data Index: 497169 (C4 (Web Text))

Max Activating Token Index: 185

Text #14

Max Range: 3.0655. Min Range: -3.0655

Max Act: 2.9548. Min Act: -0.1700

Data Index: 579087 (C4 (Web Text))

Max Activating Token Index: 429

Text #15

Max Range: 3.0655. Min Range: -3.0655

Max Act: 2.9548. Min Act: -0.1700

Data Index: 389255 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 3.0655. Min Range: -3.0655

Max Act: 2.9706. Min Act: -0.1700

Data Index: 653329 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 3.0655. Min Range: -3.0655

Max Act: 2.9231. Min Act: -0.1700

Data Index: 647853 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 3.0655. Min Range: -3.0655

Max Act: 2.9548. Min Act: -0.1700

Data Index: 1005310 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 3.0655. Min Range: -3.0655

Max Act: 2.9390. Min Act: -0.1700

Data Index: 503935 (C4 (Web Text))

Max Activating Token Index: 827