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

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

Neuron 1691 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: 3.2467. Min Range: -3.2467

Max Act: 3.2467. Min Act: -0.1700

Data Index: 1190839 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 3.2467. Min Range: -3.2467

Max Act: 3.1221. Min Act: -0.1700

Data Index: 73175 (C4 (Web Text))

Max Activating Token Index: 338

Text #2

Max Range: 3.2467. Min Range: -3.2467

Max Act: 3.1210. Min Act: -0.1700

Data Index: 429436 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 3.2467. Min Range: -3.2467

Max Act: 3.0785. Min Act: -0.1700

Data Index: 685933 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 3.2467. Min Range: -3.2467

Max Act: 3.0542. Min Act: -0.1700

Data Index: 433444 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 3.2467. Min Range: -3.2467

Max Act: 3.0225. Min Act: -0.1700

Data Index: 1320455 (C4 (Web Text))

Max Activating Token Index: 548

Text #6

Max Range: 3.2467. Min Range: -3.2467

Max Act: 3.0107. Min Act: -0.1700

Data Index: 418731 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 3.2467. Min Range: -3.2467

Max Act: 2.9894. Min Act: -0.1700

Data Index: 792296 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 3.2467. Min Range: -3.2467

Max Act: 2.9620. Min Act: -0.1700

Data Index: 58690 (C4 (Web Text))

Max Activating Token Index: 964

Text #9

Max Range: 3.2467. Min Range: -3.2467

Max Act: 2.9349. Min Act: -0.1700

Data Index: 158385 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 3.2467. Min Range: -3.2467

Max Act: 2.9198. Min Act: -0.1700

Data Index: 381538 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 3.2467. Min Range: -3.2467

Max Act: 2.9427. Min Act: -0.1700

Data Index: 348122 (C4 (Web Text))

Max Activating Token Index: 268

Text #12

Max Range: 3.2467. Min Range: -3.2467

Max Act: 2.9369. Min Act: -0.1700

Data Index: 1227711 (C4 (Web Text))

Max Activating Token Index: 979

Text #13

Max Range: 3.2467. Min Range: -3.2467

Max Act: 2.9446. Min Act: -0.1700

Data Index: 879709 (C4 (Web Text))

Max Activating Token Index: 524

Text #14

Max Range: 3.2467. Min Range: -3.2467

Max Act: 2.9207. Min Act: -0.1700

Data Index: 481020 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 3.2467. Min Range: -3.2467

Max Act: 2.9322. Min Act: -0.1700

Data Index: 547772 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 3.2467. Min Range: -3.2467

Max Act: 2.9245. Min Act: -0.1700

Data Index: 721239 (C4 (Web Text))

Max Activating Token Index: 711

Text #17

Max Range: 3.2467. Min Range: -3.2467

Max Act: 2.9468. Min Act: -0.1700

Data Index: 1089387 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 3.2467. Min Range: -3.2467

Max Act: 2.9002. Min Act: -0.1700

Data Index: 821753 (C4 (Web Text))

Max Activating Token Index: 880

Text #19

Max Range: 3.2467. Min Range: -3.2467

Max Act: 2.8920. Min Act: -0.1700

Data Index: 379718 (C4 (Web Text))

Max Activating Token Index: 280