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

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

Neuron 1030 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: 3.6946. Min Range: -3.6946

Max Act: 3.6946. Min Act: -0.1700

Data Index: 629354 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 3.6946. Min Range: -3.6946

Max Act: 3.6106. Min Act: -0.1700

Data Index: 1226860 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 3.6946. Min Range: -3.6946

Max Act: 3.5890. Min Act: -0.1700

Data Index: 16792 (C4 (Web Text))

Max Activating Token Index: 708

Text #3

Max Range: 3.6946. Min Range: -3.6946

Max Act: 3.5242. Min Act: -0.1700

Data Index: 1359720 (C4 (Web Text))

Max Activating Token Index: 821

Text #4

Max Range: 3.6946. Min Range: -3.6946

Max Act: 3.5305. Min Act: -0.1700

Data Index: 1122146 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 3.6946. Min Range: -3.6946

Max Act: 3.5514. Min Act: -0.1700

Data Index: 29821 (C4 (Web Text))

Max Activating Token Index: 595

Text #6

Max Range: 3.6946. Min Range: -3.6946

Max Act: 3.5370. Min Act: -0.1700

Data Index: 1174122 (C4 (Web Text))

Max Activating Token Index: 631

Text #7

Max Range: 3.6946. Min Range: -3.6946

Max Act: 3.5373. Min Act: -0.1700

Data Index: 144454 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 3.6946. Min Range: -3.6946

Max Act: 3.4857. Min Act: -0.1700

Data Index: 379236 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 3.6946. Min Range: -3.6946

Max Act: 3.4790. Min Act: -0.1700

Data Index: 1274814 (C4 (Web Text))

Max Activating Token Index: 566

Text #10

Max Range: 3.6946. Min Range: -3.6946

Max Act: 3.4204. Min Act: -0.1700

Data Index: 149048 (C4 (Web Text))

Max Activating Token Index: 742

Text #11

Max Range: 3.6946. Min Range: -3.6946

Max Act: 3.4731. Min Act: -0.1700

Data Index: 1144669 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 3.6946. Min Range: -3.6946

Max Act: 3.4689. Min Act: -0.1700

Data Index: 777691 (C4 (Web Text))

Max Activating Token Index: 257

Text #13

Max Range: 3.6946. Min Range: -3.6946

Max Act: 3.4127. Min Act: -0.1700

Data Index: 652049 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 3.6946. Min Range: -3.6946

Max Act: 3.4327. Min Act: -0.1700

Data Index: 1005551 (C4 (Web Text))

Max Activating Token Index: 759

Text #15

Max Range: 3.6946. Min Range: -3.6946

Max Act: 3.4126. Min Act: -0.1700

Data Index: 644419 (C4 (Web Text))

Max Activating Token Index: 479

Text #16

Max Range: 3.6946. Min Range: -3.6946

Max Act: 3.4137. Min Act: -0.1700

Data Index: 215131 (C4 (Web Text))

Max Activating Token Index: 473

Text #17

Max Range: 3.6946. Min Range: -3.6946

Max Act: 3.4279. Min Act: -0.1700

Data Index: 1143145 (C4 (Web Text))

Max Activating Token Index: 770

Text #18

Max Range: 3.6946. Min Range: -3.6946

Max Act: 3.4346. Min Act: -0.1700

Data Index: 417752 (C4 (Web Text))

Max Activating Token Index: 515

Text #19

Max Range: 3.6946. Min Range: -3.6946

Max Act: 3.4232. Min Act: -0.1700

Data Index: 812853 (C4 (Web Text))

Max Activating Token Index: 82