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

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

Neuron 2012 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: 4.5330. Min Range: -4.5330

Max Act: 4.5330. Min Act: -0.1700

Data Index: 152369 (C4 (Web Text))

Max Activating Token Index: 727

Text #1

Max Range: 4.5330. Min Range: -4.5330

Max Act: 4.2890. Min Act: -0.1700

Data Index: 1235998 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 4.5330. Min Range: -4.5330

Max Act: 4.2660. Min Act: -0.1700

Data Index: 881113 (C4 (Web Text))

Max Activating Token Index: 957

Text #3

Max Range: 4.5330. Min Range: -4.5330

Max Act: 4.2610. Min Act: -0.1700

Data Index: 1187489 (C4 (Web Text))

Max Activating Token Index: 221

Text #4

Max Range: 4.5330. Min Range: -4.5330

Max Act: 4.2252. Min Act: -0.1700

Data Index: 20697 (C4 (Web Text))

Max Activating Token Index: 851

Text #5

Max Range: 4.5330. Min Range: -4.5330

Max Act: 4.1833. Min Act: -0.1700

Data Index: 483070 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 4.5330. Min Range: -4.5330

Max Act: 4.2290. Min Act: -0.1700

Data Index: 1012168 (C4 (Web Text))

Max Activating Token Index: 457

Text #7

Max Range: 4.5330. Min Range: -4.5330

Max Act: 4.1788. Min Act: -0.1700

Data Index: 777326 (C4 (Web Text))

Max Activating Token Index: 308

Text #8

Max Range: 4.5330. Min Range: -4.5330

Max Act: 4.1587. Min Act: -0.1700

Data Index: 189780 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 4.5330. Min Range: -4.5330

Max Act: 4.1671. Min Act: -0.1700

Data Index: 23926 (C4 (Web Text))

Max Activating Token Index: 661

Text #10

Max Range: 4.5330. Min Range: -4.5330

Max Act: 4.1387. Min Act: -0.1700

Data Index: 322870 (C4 (Web Text))

Max Activating Token Index: 472

Text #11

Max Range: 4.5330. Min Range: -4.5330

Max Act: 4.1499. Min Act: -0.1700

Data Index: 906320 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 4.5330. Min Range: -4.5330

Max Act: 4.1163. Min Act: -0.1700

Data Index: 1016243 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 4.5330. Min Range: -4.5330

Max Act: 4.1327. Min Act: -0.1700

Data Index: 438729 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 4.5330. Min Range: -4.5330

Max Act: 4.0968. Min Act: -0.1700

Data Index: 1619575 (Python Code)

Max Activating Token Index: 171

Text #15

Max Range: 4.5330. Min Range: -4.5330

Max Act: 4.0926. Min Act: -0.1700

Data Index: 980182 (C4 (Web Text))

Max Activating Token Index: 232

Text #16

Max Range: 4.5330. Min Range: -4.5330

Max Act: 4.0685. Min Act: -0.1700

Data Index: 765404 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 4.5330. Min Range: -4.5330

Max Act: 4.0850. Min Act: -0.1700

Data Index: 678690 (C4 (Web Text))

Max Activating Token Index: 197

Text #18

Max Range: 4.5330. Min Range: -4.5330

Max Act: 4.0808. Min Act: -0.1700

Data Index: 256303 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 4.5330. Min Range: -4.5330

Max Act: 4.0771. Min Act: -0.1700

Data Index: 287826 (C4 (Web Text))

Max Activating Token Index: 693