Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1663 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.7028. Min Range: -3.7028

Max Act: 3.7028. Min Act: -0.1700

Data Index: 1338813 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 3.7028. Min Range: -3.7028

Max Act: 3.5988. Min Act: -0.1700

Data Index: 726387 (C4 (Web Text))

Max Activating Token Index: 982

Text #2

Max Range: 3.7028. Min Range: -3.7028

Max Act: 3.4875. Min Act: -0.1700

Data Index: 835415 (C4 (Web Text))

Max Activating Token Index: 964

Text #3

Max Range: 3.7028. Min Range: -3.7028

Max Act: 3.4963. Min Act: -0.1700

Data Index: 426035 (C4 (Web Text))

Max Activating Token Index: 629

Text #4

Max Range: 3.7028. Min Range: -3.7028

Max Act: 3.4782. Min Act: -0.1700

Data Index: 480486 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 3.7028. Min Range: -3.7028

Max Act: 3.4639. Min Act: -0.1700

Data Index: 1190868 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 3.7028. Min Range: -3.7028

Max Act: 3.4346. Min Act: -0.1700

Data Index: 325882 (C4 (Web Text))

Max Activating Token Index: 1011

Text #7

Max Range: 3.7028. Min Range: -3.7028

Max Act: 3.4442. Min Act: -0.1700

Data Index: 1282155 (C4 (Web Text))

Max Activating Token Index: 380

Text #8

Max Range: 3.7028. Min Range: -3.7028

Max Act: 3.4062. Min Act: -0.1700

Data Index: 1538188 (Python Code)

Max Activating Token Index: 145

Text #9

Max Range: 3.7028. Min Range: -3.7028

Max Act: 3.4330. Min Act: -0.1700

Data Index: 503327 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 3.7028. Min Range: -3.7028

Max Act: 3.4449. Min Act: -0.1700

Data Index: 1174329 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 3.7028. Min Range: -3.7028

Max Act: 3.4292. Min Act: -0.1700

Data Index: 668917 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 3.7028. Min Range: -3.7028

Max Act: 3.4381. Min Act: -0.1700

Data Index: 1243884 (C4 (Web Text))

Max Activating Token Index: 565

Text #13

Max Range: 3.7028. Min Range: -3.7028

Max Act: 3.4376. Min Act: -0.1700

Data Index: 1617329 (Python Code)

Max Activating Token Index: 303

Text #14

Max Range: 3.7028. Min Range: -3.7028

Max Act: 3.4517. Min Act: -0.1700

Data Index: 1542734 (Python Code)

Max Activating Token Index: 735

Text #15

Max Range: 3.7028. Min Range: -3.7028

Max Act: 3.4406. Min Act: -0.1700

Data Index: 1605539 (Python Code)

Max Activating Token Index: 49

Text #16

Max Range: 3.7028. Min Range: -3.7028

Max Act: 3.4110. Min Act: -0.1700

Data Index: 582028 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 3.7028. Min Range: -3.7028

Max Act: 3.4112. Min Act: -0.1700

Data Index: 520283 (C4 (Web Text))

Max Activating Token Index: 635

Text #18

Max Range: 3.7028. Min Range: -3.7028

Max Act: 3.3985. Min Act: -0.1700

Data Index: 1229116 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 3.7028. Min Range: -3.7028

Max Act: 3.3990. Min Act: -0.1700

Data Index: 348909 (C4 (Web Text))

Max Activating Token Index: 847