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

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

Neuron 522 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: 3.8345. Min Range: -3.8345

Max Act: 3.8345. Min Act: -0.1698

Data Index: 1184861 (C4 (Web Text))

Max Activating Token Index: 770

Text #1

Max Range: 3.8345. Min Range: -3.8345

Max Act: 3.6309. Min Act: -0.1021

Data Index: 52677 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 3.8345. Min Range: -3.8345

Max Act: 3.5936. Min Act: -0.1700

Data Index: 671806 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 3.8345. Min Range: -3.8345

Max Act: 3.5600. Min Act: -0.1135

Data Index: 508251 (C4 (Web Text))

Max Activating Token Index: 959

Text #4

Max Range: 3.8345. Min Range: -3.8345

Max Act: 3.5640. Min Act: -0.1700

Data Index: 702158 (C4 (Web Text))

Max Activating Token Index: 595

Text #5

Max Range: 3.8345. Min Range: -3.8345

Max Act: 3.5504. Min Act: -0.1699

Data Index: 233692 (C4 (Web Text))

Max Activating Token Index: 660

Text #6

Max Range: 3.8345. Min Range: -3.8345

Max Act: 3.5282. Min Act: -0.0476

Data Index: 526705 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 3.8345. Min Range: -3.8345

Max Act: 3.5287. Min Act: -0.1700

Data Index: 161900 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 3.8345. Min Range: -3.8345

Max Act: 3.5440. Min Act: -0.0476

Data Index: 464838 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 3.8345. Min Range: -3.8345

Max Act: 3.5387. Min Act: -0.1308

Data Index: 162380 (C4 (Web Text))

Max Activating Token Index: 176

Text #10

Max Range: 3.8345. Min Range: -3.8345

Max Act: 3.5048. Min Act: -0.1700

Data Index: 687255 (C4 (Web Text))

Max Activating Token Index: 788

Text #11

Max Range: 3.8345. Min Range: -3.8345

Max Act: 3.4946. Min Act: -0.1700

Data Index: 299817 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 3.8345. Min Range: -3.8345

Max Act: 3.4981. Min Act: -0.0476

Data Index: 1305438 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 3.8345. Min Range: -3.8345

Max Act: 3.4778. Min Act: -0.0476

Data Index: 1259965 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 3.8345. Min Range: -3.8345

Max Act: 3.4938. Min Act: -0.1598

Data Index: 733926 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 3.8345. Min Range: -3.8345

Max Act: 3.4585. Min Act: -0.1700

Data Index: 112217 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 3.8345. Min Range: -3.8345

Max Act: 3.4809. Min Act: -0.1297

Data Index: 1242574 (C4 (Web Text))

Max Activating Token Index: 110

Text #17

Max Range: 3.8345. Min Range: -3.8345

Max Act: 3.4869. Min Act: -0.0476

Data Index: 656739 (C4 (Web Text))

Max Activating Token Index: 211

Text #18

Max Range: 3.8345. Min Range: -3.8345

Max Act: 3.4646. Min Act: -0.1694

Data Index: 438775 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 3.8345. Min Range: -3.8345

Max Act: 3.4790. Min Act: -0.1700

Data Index: 914867 (C4 (Web Text))

Max Activating Token Index: 68