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

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

Neuron 1688 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: 3.5274. Min Range: -3.5274

Max Act: 3.5274. Min Act: -0.1700

Data Index: 119642 (C4 (Web Text))

Max Activating Token Index: 561

Text #1

Max Range: 3.5274. Min Range: -3.5274

Max Act: 3.4626. Min Act: -0.1700

Data Index: 1059975 (C4 (Web Text))

Max Activating Token Index: 822

Text #2

Max Range: 3.5274. Min Range: -3.5274

Max Act: 3.4423. Min Act: -0.1699

Data Index: 120941 (C4 (Web Text))

Max Activating Token Index: 583

Text #3

Max Range: 3.5274. Min Range: -3.5274

Max Act: 3.4324. Min Act: -0.1700

Data Index: 342328 (C4 (Web Text))

Max Activating Token Index: 486

Text #4

Max Range: 3.5274. Min Range: -3.5274

Max Act: 3.4058. Min Act: -0.1700

Data Index: 756867 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 3.5274. Min Range: -3.5274

Max Act: 3.4033. Min Act: -0.1700

Data Index: 992088 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 3.5274. Min Range: -3.5274

Max Act: 3.4202. Min Act: -0.1700

Data Index: 1084173 (C4 (Web Text))

Max Activating Token Index: 386

Text #7

Max Range: 3.5274. Min Range: -3.5274

Max Act: 3.3762. Min Act: -0.1700

Data Index: 942877 (C4 (Web Text))

Max Activating Token Index: 52

Text #8

Max Range: 3.5274. Min Range: -3.5274

Max Act: 3.3716. Min Act: -0.1700

Data Index: 931934 (C4 (Web Text))

Max Activating Token Index: 62

Text #9

Max Range: 3.5274. Min Range: -3.5274

Max Act: 3.3751. Min Act: -0.1700

Data Index: 1168204 (C4 (Web Text))

Max Activating Token Index: 784

Text #10

Max Range: 3.5274. Min Range: -3.5274

Max Act: 3.3534. Min Act: -0.1700

Data Index: 962154 (C4 (Web Text))

Max Activating Token Index: 895

Text #11

Max Range: 3.5274. Min Range: -3.5274

Max Act: 3.3577. Min Act: -0.1700

Data Index: 883374 (C4 (Web Text))

Max Activating Token Index: 690

Text #12

Max Range: 3.5274. Min Range: -3.5274

Max Act: 3.3406. Min Act: -0.1698

Data Index: 67940 (C4 (Web Text))

Max Activating Token Index: 697

Text #13

Max Range: 3.5274. Min Range: -3.5274

Max Act: 3.3156. Min Act: -0.1700

Data Index: 1095312 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 3.5274. Min Range: -3.5274

Max Act: 3.3211. Min Act: -0.1700

Data Index: 885212 (C4 (Web Text))

Max Activating Token Index: 232

Text #15

Max Range: 3.5274. Min Range: -3.5274

Max Act: 3.3183. Min Act: -0.1699

Data Index: 1332595 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 3.5274. Min Range: -3.5274

Max Act: 3.3083. Min Act: -0.1700

Data Index: 295463 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 3.5274. Min Range: -3.5274

Max Act: 3.3019. Min Act: -0.1700

Data Index: 54023 (C4 (Web Text))

Max Activating Token Index: 277

Text #18

Max Range: 3.5274. Min Range: -3.5274

Max Act: 3.2929. Min Act: -0.1700

Data Index: 52369 (C4 (Web Text))

Max Activating Token Index: 454

Text #19

Max Range: 3.5274. Min Range: -3.5274

Max Act: 3.2892. Min Act: -0.1700

Data Index: 100471 (C4 (Web Text))

Max Activating Token Index: 566