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

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

Neuron 1033 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: 3.4443. Min Range: -3.4443

Max Act: 3.4443. Min Act: -0.1700

Data Index: 107129 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 3.4443. Min Range: -3.4443

Max Act: 3.4369. Min Act: -0.1700

Data Index: 8561 (C4 (Web Text))

Max Activating Token Index: 462

Text #2

Max Range: 3.4443. Min Range: -3.4443

Max Act: 3.3382. Min Act: -0.1700

Data Index: 355378 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 3.4443. Min Range: -3.4443

Max Act: 3.3477. Min Act: -0.1700

Data Index: 767692 (C4 (Web Text))

Max Activating Token Index: 489

Text #4

Max Range: 3.4443. Min Range: -3.4443

Max Act: 3.3296. Min Act: -0.1699

Data Index: 297116 (C4 (Web Text))

Max Activating Token Index: 812

Text #5

Max Range: 3.4443. Min Range: -3.4443

Max Act: 3.3166. Min Act: -0.1700

Data Index: 111533 (C4 (Web Text))

Max Activating Token Index: 685

Text #6

Max Range: 3.4443. Min Range: -3.4443

Max Act: 3.3086. Min Act: -0.1700

Data Index: 1176975 (C4 (Web Text))

Max Activating Token Index: 837

Text #7

Max Range: 3.4443. Min Range: -3.4443

Max Act: 3.2853. Min Act: -0.1700

Data Index: 1513521 (Python Code)

Max Activating Token Index: 904

Text #8

Max Range: 3.4443. Min Range: -3.4443

Max Act: 3.2233. Min Act: -0.1700

Data Index: 1152396 (C4 (Web Text))

Max Activating Token Index: 973

Text #9

Max Range: 3.4443. Min Range: -3.4443

Max Act: 3.2291. Min Act: -0.1700

Data Index: 1178077 (C4 (Web Text))

Max Activating Token Index: 406

Text #10

Max Range: 3.4443. Min Range: -3.4443

Max Act: 3.2151. Min Act: -0.1700

Data Index: 1288793 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 3.4443. Min Range: -3.4443

Max Act: 3.2274. Min Act: -0.1700

Data Index: 1304829 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 3.4443. Min Range: -3.4443

Max Act: 3.2107. Min Act: -0.1700

Data Index: 645103 (C4 (Web Text))

Max Activating Token Index: 186

Text #13

Max Range: 3.4443. Min Range: -3.4443

Max Act: 3.2199. Min Act: -0.1700

Data Index: 141991 (C4 (Web Text))

Max Activating Token Index: 537

Text #14

Max Range: 3.4443. Min Range: -3.4443

Max Act: 3.1924. Min Act: -0.1700

Data Index: 405230 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 3.4443. Min Range: -3.4443

Max Act: 3.2123. Min Act: -0.1700

Data Index: 774715 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 3.4443. Min Range: -3.4443

Max Act: 3.2262. Min Act: -0.1700

Data Index: 631202 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 3.4443. Min Range: -3.4443

Max Act: 3.2563. Min Act: -0.1700

Data Index: 372779 (C4 (Web Text))

Max Activating Token Index: 773

Text #18

Max Range: 3.4443. Min Range: -3.4443

Max Act: 3.2117. Min Act: -0.1700

Data Index: 1276960 (C4 (Web Text))

Max Activating Token Index: 183

Text #19

Max Range: 3.4443. Min Range: -3.4443

Max Act: 3.2280. Min Act: -0.1700

Data Index: 640723 (C4 (Web Text))

Max Activating Token Index: 797