Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 595 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 7.0355. Min Range: -7.0355

Max Act: 7.0355. Min Act: -0.1700

Data Index: 18445 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 7.0355. Min Range: -7.0355

Max Act: 6.8480. Min Act: -0.1700

Data Index: 896201 (C4 (Web Text))

Max Activating Token Index: 524

Text #2

Max Range: 7.0355. Min Range: -7.0355

Max Act: 6.6605. Min Act: -0.1700

Data Index: 263484 (C4 (Web Text))

Max Activating Token Index: 423

Text #3

Max Range: 7.0355. Min Range: -7.0355

Max Act: 6.5980. Min Act: -0.1700

Data Index: 45982 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 7.0355. Min Range: -7.0355

Max Act: 6.5980. Min Act: -0.1700

Data Index: 791969 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 7.0355. Min Range: -7.0355

Max Act: 6.5355. Min Act: -0.1700

Data Index: 550913 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 7.0355. Min Range: -7.0355

Max Act: 6.4417. Min Act: -0.1700

Data Index: 176948 (C4 (Web Text))

Max Activating Token Index: 382

Text #7

Max Range: 7.0355. Min Range: -7.0355

Max Act: 6.4417. Min Act: -0.1700

Data Index: 458674 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 7.0355. Min Range: -7.0355

Max Act: 6.4730. Min Act: -0.1700

Data Index: 431915 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 7.0355. Min Range: -7.0355

Max Act: 6.3167. Min Act: -0.1700

Data Index: 927823 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 7.0355. Min Range: -7.0355

Max Act: 6.3792. Min Act: -0.1700

Data Index: 603827 (C4 (Web Text))

Max Activating Token Index: 625

Text #11

Max Range: 7.0355. Min Range: -7.0355

Max Act: 6.3167. Min Act: -0.1700

Data Index: 1002081 (C4 (Web Text))

Max Activating Token Index: 264

Text #12

Max Range: 7.0355. Min Range: -7.0355

Max Act: 6.3167. Min Act: -0.1700

Data Index: 46806 (C4 (Web Text))

Max Activating Token Index: 122

Text #13

Max Range: 7.0355. Min Range: -7.0355

Max Act: 6.3167. Min Act: -0.1700

Data Index: 126272 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 7.0355. Min Range: -7.0355

Max Act: 6.2230. Min Act: -0.1700

Data Index: 615872 (C4 (Web Text))

Max Activating Token Index: 909

Text #15

Max Range: 7.0355. Min Range: -7.0355

Max Act: 6.2855. Min Act: -0.1700

Data Index: 659557 (C4 (Web Text))

Max Activating Token Index: 243

Text #16

Max Range: 7.0355. Min Range: -7.0355

Max Act: 6.2542. Min Act: -0.1700

Data Index: 5097 (C4 (Web Text))

Max Activating Token Index: 205

Text #17

Max Range: 7.0355. Min Range: -7.0355

Max Act: 6.1605. Min Act: -0.1700

Data Index: 906964 (C4 (Web Text))

Max Activating Token Index: 469

Text #18

Max Range: 7.0355. Min Range: -7.0355

Max Act: 6.1605. Min Act: -0.1699

Data Index: 418420 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 7.0355. Min Range: -7.0355

Max Act: 6.1292. Min Act: -0.1700

Data Index: 612588 (C4 (Web Text))

Max Activating Token Index: 468