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

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

Neuron 225 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: 3.6270. Min Range: -3.6270

Max Act: 3.6270. Min Act: -0.1700

Data Index: 701393 (C4 (Web Text))

Max Activating Token Index: 250

Text #1

Max Range: 3.6270. Min Range: -3.6270

Max Act: 3.5484. Min Act: -0.1700

Data Index: 230628 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 3.6270. Min Range: -3.6270

Max Act: 3.5115. Min Act: -0.1700

Data Index: 810707 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 3.6270. Min Range: -3.6270

Max Act: 3.4908. Min Act: -0.1700

Data Index: 282479 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 3.6270. Min Range: -3.6270

Max Act: 3.4081. Min Act: -0.1700

Data Index: 1047890 (C4 (Web Text))

Max Activating Token Index: 814

Text #5

Max Range: 3.6270. Min Range: -3.6270

Max Act: 3.4784. Min Act: -0.1700

Data Index: 1332744 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 3.6270. Min Range: -3.6270

Max Act: 3.4602. Min Act: -0.1700

Data Index: 546656 (C4 (Web Text))

Max Activating Token Index: 988

Text #7

Max Range: 3.6270. Min Range: -3.6270

Max Act: 3.4332. Min Act: -0.1700

Data Index: 83249 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 3.6270. Min Range: -3.6270

Max Act: 3.4254. Min Act: -0.1700

Data Index: 1290068 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 3.6270. Min Range: -3.6270

Max Act: 3.3542. Min Act: -0.1700

Data Index: 1319605 (C4 (Web Text))

Max Activating Token Index: 498

Text #10

Max Range: 3.6270. Min Range: -3.6270

Max Act: 3.3520. Min Act: -0.1700

Data Index: 566759 (C4 (Web Text))

Max Activating Token Index: 153

Text #11

Max Range: 3.6270. Min Range: -3.6270

Max Act: 3.3228. Min Act: -0.1700

Data Index: 959507 (C4 (Web Text))

Max Activating Token Index: 151

Text #12

Max Range: 3.6270. Min Range: -3.6270

Max Act: 3.3009. Min Act: -0.1700

Data Index: 930379 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 3.6270. Min Range: -3.6270

Max Act: 3.3257. Min Act: -0.1700

Data Index: 1115666 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 3.6270. Min Range: -3.6270

Max Act: 3.3368. Min Act: -0.1700

Data Index: 547959 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 3.6270. Min Range: -3.6270

Max Act: 3.3008. Min Act: -0.1700

Data Index: 741201 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 3.6270. Min Range: -3.6270

Max Act: 3.3007. Min Act: -0.1700

Data Index: 194850 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 3.6270. Min Range: -3.6270

Max Act: 3.3060. Min Act: -0.1700

Data Index: 232255 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 3.6270. Min Range: -3.6270

Max Act: 3.2837. Min Act: -0.1700

Data Index: 1310151 (C4 (Web Text))

Max Activating Token Index: 972

Text #19

Max Range: 3.6270. Min Range: -3.6270

Max Act: 3.2783. Min Act: -0.1700

Data Index: 885054 (C4 (Web Text))

Max Activating Token Index: 218