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

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

Neuron 27 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: 3.3877. Min Range: -3.3877

Max Act: 3.3877. Min Act: -0.1700

Data Index: 1336607 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 3.3877. Min Range: -3.3877

Max Act: 3.3585. Min Act: -0.1700

Data Index: 265616 (C4 (Web Text))

Max Activating Token Index: 321

Text #2

Max Range: 3.3877. Min Range: -3.3877

Max Act: 3.3617. Min Act: -0.1700

Data Index: 707454 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 3.3877. Min Range: -3.3877

Max Act: 3.3110. Min Act: -0.1700

Data Index: 964612 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 3.3877. Min Range: -3.3877

Max Act: 3.3041. Min Act: -0.1700

Data Index: 545932 (C4 (Web Text))

Max Activating Token Index: 233

Text #5

Max Range: 3.3877. Min Range: -3.3877

Max Act: 3.2902. Min Act: -0.1700

Data Index: 1254626 (C4 (Web Text))

Max Activating Token Index: 339

Text #6

Max Range: 3.3877. Min Range: -3.3877

Max Act: 3.2699. Min Act: -0.1700

Data Index: 1223271 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 3.3877. Min Range: -3.3877

Max Act: 3.2652. Min Act: -0.1700

Data Index: 1176052 (C4 (Web Text))

Max Activating Token Index: 994

Text #8

Max Range: 3.3877. Min Range: -3.3877

Max Act: 3.2704. Min Act: -0.1700

Data Index: 956046 (C4 (Web Text))

Max Activating Token Index: 815

Text #9

Max Range: 3.3877. Min Range: -3.3877

Max Act: 3.2334. Min Act: -0.1700

Data Index: 717503 (C4 (Web Text))

Max Activating Token Index: 778

Text #10

Max Range: 3.3877. Min Range: -3.3877

Max Act: 3.2491. Min Act: -0.1700

Data Index: 230331 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 3.3877. Min Range: -3.3877

Max Act: 3.2436. Min Act: -0.1700

Data Index: 729680 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 3.3877. Min Range: -3.3877

Max Act: 3.2281. Min Act: -0.1700

Data Index: 796286 (C4 (Web Text))

Max Activating Token Index: 496

Text #13

Max Range: 3.3877. Min Range: -3.3877

Max Act: 3.2341. Min Act: -0.1700

Data Index: 671743 (C4 (Web Text))

Max Activating Token Index: 645

Text #14

Max Range: 3.3877. Min Range: -3.3877

Max Act: 3.2225. Min Act: -0.1700

Data Index: 1284216 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 3.3877. Min Range: -3.3877

Max Act: 3.2139. Min Act: -0.1700

Data Index: 325519 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 3.3877. Min Range: -3.3877

Max Act: 3.2165. Min Act: -0.1700

Data Index: 1022440 (C4 (Web Text))

Max Activating Token Index: 952

Text #17

Max Range: 3.3877. Min Range: -3.3877

Max Act: 3.2253. Min Act: -0.1700

Data Index: 353422 (C4 (Web Text))

Max Activating Token Index: 632

Text #18

Max Range: 3.3877. Min Range: -3.3877

Max Act: 3.2107. Min Act: -0.1700

Data Index: 50322 (C4 (Web Text))

Max Activating Token Index: 845

Text #19

Max Range: 3.3877. Min Range: -3.3877

Max Act: 3.2140. Min Act: -0.1700

Data Index: 726032 (C4 (Web Text))

Max Activating Token Index: 580