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

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

Neuron 1923 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: 4.3909. Min Range: -4.3909

Max Act: 4.3909. Min Act: -0.1700

Data Index: 164936 (C4 (Web Text))

Max Activating Token Index: 376

Text #1

Max Range: 4.3909. Min Range: -4.3909

Max Act: 4.3845. Min Act: -0.1700

Data Index: 1060970 (C4 (Web Text))

Max Activating Token Index: 711

Text #2

Max Range: 4.3909. Min Range: -4.3909

Max Act: 4.3613. Min Act: -0.1700

Data Index: 1300381 (C4 (Web Text))

Max Activating Token Index: 575

Text #3

Max Range: 4.3909. Min Range: -4.3909

Max Act: 4.3573. Min Act: -0.1700

Data Index: 1297439 (C4 (Web Text))

Max Activating Token Index: 365

Text #4

Max Range: 4.3909. Min Range: -4.3909

Max Act: 4.3175. Min Act: -0.1700

Data Index: 1150685 (C4 (Web Text))

Max Activating Token Index: 687

Text #5

Max Range: 4.3909. Min Range: -4.3909

Max Act: 4.3388. Min Act: -0.1700

Data Index: 1319642 (C4 (Web Text))

Max Activating Token Index: 410

Text #6

Max Range: 4.3909. Min Range: -4.3909

Max Act: 4.3444. Min Act: -0.1700

Data Index: 1122357 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 4.3909. Min Range: -4.3909

Max Act: 4.3456. Min Act: -0.1700

Data Index: 672555 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 4.3909. Min Range: -4.3909

Max Act: 4.3254. Min Act: -0.1700

Data Index: 624693 (C4 (Web Text))

Max Activating Token Index: 496

Text #9

Max Range: 4.3909. Min Range: -4.3909

Max Act: 4.3317. Min Act: -0.1700

Data Index: 320811 (C4 (Web Text))

Max Activating Token Index: 475

Text #10

Max Range: 4.3909. Min Range: -4.3909

Max Act: 4.3372. Min Act: -0.1700

Data Index: 812635 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 4.3909. Min Range: -4.3909

Max Act: 4.3429. Min Act: -0.1700

Data Index: 960789 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 4.3909. Min Range: -4.3909

Max Act: 4.3097. Min Act: -0.1700

Data Index: 1453799 (Python Code)

Max Activating Token Index: 503

Text #13

Max Range: 4.3909. Min Range: -4.3909

Max Act: 4.2913. Min Act: -0.1700

Data Index: 1582350 (Python Code)

Max Activating Token Index: 437

Text #14

Max Range: 4.3909. Min Range: -4.3909

Max Act: 4.2818. Min Act: -0.1700

Data Index: 270276 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 4.3909. Min Range: -4.3909

Max Act: 4.2722. Min Act: -0.1700

Data Index: 33118 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 4.3909. Min Range: -4.3909

Max Act: 4.2880. Min Act: -0.1700

Data Index: 1319121 (C4 (Web Text))

Max Activating Token Index: 421

Text #17

Max Range: 4.3909. Min Range: -4.3909

Max Act: 4.2901. Min Act: -0.1700

Data Index: 33132 (C4 (Web Text))

Max Activating Token Index: 309

Text #18

Max Range: 4.3909. Min Range: -4.3909

Max Act: 4.2948. Min Act: -0.1700

Data Index: 1288942 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 4.3909. Min Range: -4.3909

Max Act: 4.2752. Min Act: -0.1700

Data Index: 713580 (C4 (Web Text))

Max Activating Token Index: 1012