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

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

Neuron 1630 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: 3.5008. Min Range: -3.5008

Max Act: 3.5008. Min Act: -0.1700

Data Index: 519638 (C4 (Web Text))

Max Activating Token Index: 746

Text #1

Max Range: 3.5008. Min Range: -3.5008

Max Act: 3.4672. Min Act: -0.1700

Data Index: 231904 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 3.5008. Min Range: -3.5008

Max Act: 3.3544. Min Act: -0.1700

Data Index: 199613 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 3.5008. Min Range: -3.5008

Max Act: 3.3534. Min Act: -0.1700

Data Index: 707516 (C4 (Web Text))

Max Activating Token Index: 497

Text #4

Max Range: 3.5008. Min Range: -3.5008

Max Act: 3.3398. Min Act: -0.1700

Data Index: 876847 (C4 (Web Text))

Max Activating Token Index: 144

Text #5

Max Range: 3.5008. Min Range: -3.5008

Max Act: 3.3492. Min Act: -0.1700

Data Index: 831165 (C4 (Web Text))

Max Activating Token Index: 381

Text #6

Max Range: 3.5008. Min Range: -3.5008

Max Act: 3.3540. Min Act: -0.1700

Data Index: 608833 (C4 (Web Text))

Max Activating Token Index: 483

Text #7

Max Range: 3.5008. Min Range: -3.5008

Max Act: 3.3420. Min Act: -0.1700

Data Index: 556122 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 3.5008. Min Range: -3.5008

Max Act: 3.3343. Min Act: -0.1700

Data Index: 208643 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 3.5008. Min Range: -3.5008

Max Act: 3.3188. Min Act: -0.1700

Data Index: 479250 (C4 (Web Text))

Max Activating Token Index: 586

Text #10

Max Range: 3.5008. Min Range: -3.5008

Max Act: 3.3254. Min Act: -0.1700

Data Index: 82513 (C4 (Web Text))

Max Activating Token Index: 552

Text #11

Max Range: 3.5008. Min Range: -3.5008

Max Act: 3.3299. Min Act: -0.1700

Data Index: 697653 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 3.5008. Min Range: -3.5008

Max Act: 3.3161. Min Act: -0.1700

Data Index: 435993 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 3.5008. Min Range: -3.5008

Max Act: 3.3055. Min Act: -0.1700

Data Index: 695092 (C4 (Web Text))

Max Activating Token Index: 460

Text #14

Max Range: 3.5008. Min Range: -3.5008

Max Act: 3.3092. Min Act: -0.1700

Data Index: 334772 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 3.5008. Min Range: -3.5008

Max Act: 3.3194. Min Act: -0.1700

Data Index: 228003 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 3.5008. Min Range: -3.5008

Max Act: 3.3038. Min Act: -0.1700

Data Index: 606625 (C4 (Web Text))

Max Activating Token Index: 360

Text #17

Max Range: 3.5008. Min Range: -3.5008

Max Act: 3.3109. Min Act: -0.1700

Data Index: 732040 (C4 (Web Text))

Max Activating Token Index: 354

Text #18

Max Range: 3.5008. Min Range: -3.5008

Max Act: 3.3076. Min Act: -0.1700

Data Index: 482984 (C4 (Web Text))

Max Activating Token Index: 550

Text #19

Max Range: 3.5008. Min Range: -3.5008

Max Act: 3.3021. Min Act: -0.1700

Data Index: 627195 (C4 (Web Text))

Max Activating Token Index: 135