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

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

Neuron 771 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: 4.7544. Min Range: -4.7544

Max Act: 4.7544. Min Act: -0.1700

Data Index: 765168 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 4.7544. Min Range: -4.7544

Max Act: 4.4755. Min Act: -0.1700

Data Index: 1357629 (C4 (Web Text))

Max Activating Token Index: 436

Text #2

Max Range: 4.7544. Min Range: -4.7544

Max Act: 4.4718. Min Act: -0.1699

Data Index: 854773 (C4 (Web Text))

Max Activating Token Index: 575

Text #3

Max Range: 4.7544. Min Range: -4.7544

Max Act: 4.4444. Min Act: -0.1699

Data Index: 632826 (C4 (Web Text))

Max Activating Token Index: 461

Text #4

Max Range: 4.7544. Min Range: -4.7544

Max Act: 4.4226. Min Act: -0.1700

Data Index: 1477938 (Python Code)

Max Activating Token Index: 692

Text #5

Max Range: 4.7544. Min Range: -4.7544

Max Act: 4.4037. Min Act: -0.1700

Data Index: 1141475 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 4.7544. Min Range: -4.7544

Max Act: 4.4083. Min Act: -0.1700

Data Index: 1198970 (C4 (Web Text))

Max Activating Token Index: 398

Text #7

Max Range: 4.7544. Min Range: -4.7544

Max Act: 4.4111. Min Act: -0.1700

Data Index: 445614 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 4.7544. Min Range: -4.7544

Max Act: 4.3807. Min Act: -0.1700

Data Index: 1327997 (C4 (Web Text))

Max Activating Token Index: 974

Text #9

Max Range: 4.7544. Min Range: -4.7544

Max Act: 4.4070. Min Act: -0.1700

Data Index: 1327443 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 4.7544. Min Range: -4.7544

Max Act: 4.3950. Min Act: -0.1700

Data Index: 1625606 (Python Code)

Max Activating Token Index: 421

Text #11

Max Range: 4.7544. Min Range: -4.7544

Max Act: 4.3748. Min Act: -0.1699

Data Index: 1460108 (Python Code)

Max Activating Token Index: 526

Text #12

Max Range: 4.7544. Min Range: -4.7544

Max Act: 4.3417. Min Act: -0.1700

Data Index: 1450800 (Python Code)

Max Activating Token Index: 72

Text #13

Max Range: 4.7544. Min Range: -4.7544

Max Act: 4.3355. Min Act: -0.1700

Data Index: 1234366 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 4.7544. Min Range: -4.7544

Max Act: 4.3016. Min Act: -0.1700

Data Index: 680378 (C4 (Web Text))

Max Activating Token Index: 141

Text #15

Max Range: 4.7544. Min Range: -4.7544

Max Act: 4.3353. Min Act: -0.1698

Data Index: 417026 (C4 (Web Text))

Max Activating Token Index: 984

Text #16

Max Range: 4.7544. Min Range: -4.7544

Max Act: 4.3301. Min Act: -0.1700

Data Index: 99255 (C4 (Web Text))

Max Activating Token Index: 434

Text #17

Max Range: 4.7544. Min Range: -4.7544

Max Act: 4.2782. Min Act: -0.1700

Data Index: 1324891 (C4 (Web Text))

Max Activating Token Index: 451

Text #18

Max Range: 4.7544. Min Range: -4.7544

Max Act: 4.2580. Min Act: -0.1700

Data Index: 321416 (C4 (Web Text))

Max Activating Token Index: 881

Text #19

Max Range: 4.7544. Min Range: -4.7544

Max Act: 4.2853. Min Act: -0.1700

Data Index: 1458431 (Python Code)

Max Activating Token Index: 544