Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1532 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.5629. Min Range: -3.5629

Max Act: 3.5629. Min Act: -0.1700

Data Index: 1303168 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 3.5629. Min Range: -3.5629

Max Act: 3.5315. Min Act: -0.1700

Data Index: 908214 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 3.5629. Min Range: -3.5629

Max Act: 3.5002. Min Act: -0.1700

Data Index: 216603 (C4 (Web Text))

Max Activating Token Index: 331

Text #3

Max Range: 3.5629. Min Range: -3.5629

Max Act: 3.4689. Min Act: -0.1700

Data Index: 1047386 (C4 (Web Text))

Max Activating Token Index: 1001

Text #4

Max Range: 3.5629. Min Range: -3.5629

Max Act: 3.4218. Min Act: -0.1700

Data Index: 117668 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 3.5629. Min Range: -3.5629

Max Act: 3.4532. Min Act: -0.1700

Data Index: 853329 (C4 (Web Text))

Max Activating Token Index: 466

Text #6

Max Range: 3.5629. Min Range: -3.5629

Max Act: 3.4532. Min Act: -0.1700

Data Index: 717799 (C4 (Web Text))

Max Activating Token Index: 321

Text #7

Max Range: 3.5629. Min Range: -3.5629

Max Act: 3.4061. Min Act: -0.1700

Data Index: 429534 (C4 (Web Text))

Max Activating Token Index: 597

Text #8

Max Range: 3.5629. Min Range: -3.5629

Max Act: 3.4532. Min Act: -0.1700

Data Index: 1012995 (C4 (Web Text))

Max Activating Token Index: 269

Text #9

Max Range: 3.5629. Min Range: -3.5629

Max Act: 3.4375. Min Act: -0.1700

Data Index: 410989 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 3.5629. Min Range: -3.5629

Max Act: 3.4375. Min Act: -0.1700

Data Index: 1006849 (C4 (Web Text))

Max Activating Token Index: 440

Text #11

Max Range: 3.5629. Min Range: -3.5629

Max Act: 3.4218. Min Act: -0.1700

Data Index: 511084 (C4 (Web Text))

Max Activating Token Index: 720

Text #12

Max Range: 3.5629. Min Range: -3.5629

Max Act: 3.4218. Min Act: -0.1700

Data Index: 1161216 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 3.5629. Min Range: -3.5629

Max Act: 3.3905. Min Act: -0.1700

Data Index: 363557 (C4 (Web Text))

Max Activating Token Index: 942

Text #14

Max Range: 3.5629. Min Range: -3.5629

Max Act: 3.4061. Min Act: -0.1700

Data Index: 44192 (C4 (Web Text))

Max Activating Token Index: 471

Text #15

Max Range: 3.5629. Min Range: -3.5629

Max Act: 3.4218. Min Act: -0.1700

Data Index: 371884 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 3.5629. Min Range: -3.5629

Max Act: 3.3905. Min Act: -0.1700

Data Index: 962333 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 3.5629. Min Range: -3.5629

Max Act: 3.3591. Min Act: -0.1700

Data Index: 363054 (C4 (Web Text))

Max Activating Token Index: 903

Text #18

Max Range: 3.5629. Min Range: -3.5629

Max Act: 3.4061. Min Act: -0.1700

Data Index: 308571 (C4 (Web Text))

Max Activating Token Index: 177

Text #19

Max Range: 3.5629. Min Range: -3.5629

Max Act: 3.3277. Min Act: -0.1700

Data Index: 580186 (C4 (Web Text))

Max Activating Token Index: 664