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

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

Neuron 655 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: 3.6872. Min Range: -3.6872

Max Act: 3.6872. Min Act: -0.1700

Data Index: 863151 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 3.6872. Min Range: -3.6872

Max Act: 3.4722. Min Act: -0.1700

Data Index: 718901 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 3.6872. Min Range: -3.6872

Max Act: 3.4350. Min Act: -0.1700

Data Index: 965107 (C4 (Web Text))

Max Activating Token Index: 357

Text #3

Max Range: 3.6872. Min Range: -3.6872

Max Act: 3.4236. Min Act: -0.1700

Data Index: 151246 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 3.6872. Min Range: -3.6872

Max Act: 3.4181. Min Act: -0.1700

Data Index: 577763 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 3.6872. Min Range: -3.6872

Max Act: 3.4114. Min Act: -0.1700

Data Index: 1119220 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 3.6872. Min Range: -3.6872

Max Act: 3.4562. Min Act: -0.1700

Data Index: 761715 (C4 (Web Text))

Max Activating Token Index: 656

Text #7

Max Range: 3.6872. Min Range: -3.6872

Max Act: 3.3583. Min Act: -0.1700

Data Index: 399722 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 3.6872. Min Range: -3.6872

Max Act: 3.3651. Min Act: -0.1700

Data Index: 1555888 (Python Code)

Max Activating Token Index: 488

Text #9

Max Range: 3.6872. Min Range: -3.6872

Max Act: 3.3656. Min Act: -0.1700

Data Index: 338070 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 3.6872. Min Range: -3.6872

Max Act: 3.3338. Min Act: -0.1700

Data Index: 814077 (C4 (Web Text))

Max Activating Token Index: 761

Text #11

Max Range: 3.6872. Min Range: -3.6872

Max Act: 3.3404. Min Act: -0.1700

Data Index: 307295 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 3.6872. Min Range: -3.6872

Max Act: 3.3345. Min Act: -0.1700

Data Index: 773031 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 3.6872. Min Range: -3.6872

Max Act: 3.3419. Min Act: -0.1700

Data Index: 297155 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 3.6872. Min Range: -3.6872

Max Act: 3.3365. Min Act: -0.1700

Data Index: 1556311 (Python Code)

Max Activating Token Index: 16

Text #15

Max Range: 3.6872. Min Range: -3.6872

Max Act: 3.3455. Min Act: -0.1700

Data Index: 1025275 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 3.6872. Min Range: -3.6872

Max Act: 3.3428. Min Act: -0.1700

Data Index: 363712 (C4 (Web Text))

Max Activating Token Index: 1013

Text #17

Max Range: 3.6872. Min Range: -3.6872

Max Act: 3.3286. Min Act: -0.1700

Data Index: 1017672 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 3.6872. Min Range: -3.6872

Max Act: 3.2831. Min Act: -0.1700

Data Index: 1326619 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 3.6872. Min Range: -3.6872

Max Act: 3.2982. Min Act: -0.1700

Data Index: 957432 (C4 (Web Text))

Max Activating Token Index: 796