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

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

Neuron 1038 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: 3.8787. Min Range: -3.8787

Max Act: 3.8787. Min Act: -0.1700

Data Index: 589604 (C4 (Web Text))

Max Activating Token Index: 586

Text #1

Max Range: 3.8787. Min Range: -3.8787

Max Act: 3.6284. Min Act: -0.1700

Data Index: 436538 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 3.8787. Min Range: -3.8787

Max Act: 3.5344. Min Act: -0.1700

Data Index: 441958 (C4 (Web Text))

Max Activating Token Index: 510

Text #3

Max Range: 3.8787. Min Range: -3.8787

Max Act: 3.5344. Min Act: -0.1700

Data Index: 1023683 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 3.8787. Min Range: -3.8787

Max Act: 3.5344. Min Act: -0.1700

Data Index: 1358362 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 3.8787. Min Range: -3.8787

Max Act: 3.5344. Min Act: -0.1700

Data Index: 358603 (C4 (Web Text))

Max Activating Token Index: 782

Text #6

Max Range: 3.8787. Min Range: -3.8787

Max Act: 3.4874. Min Act: -0.1700

Data Index: 825541 (C4 (Web Text))

Max Activating Token Index: 431

Text #7

Max Range: 3.8787. Min Range: -3.8787

Max Act: 3.4247. Min Act: -0.1700

Data Index: 1236362 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 3.8787. Min Range: -3.8787

Max Act: 3.4874. Min Act: -0.1700

Data Index: 138375 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 3.8787. Min Range: -3.8787

Max Act: 3.4561. Min Act: -0.1700

Data Index: 271739 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 3.8787. Min Range: -3.8787

Max Act: 3.4247. Min Act: -0.1700

Data Index: 824668 (C4 (Web Text))

Max Activating Token Index: 925

Text #11

Max Range: 3.8787. Min Range: -3.8787

Max Act: 3.4247. Min Act: -0.1700

Data Index: 4376 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 3.8787. Min Range: -3.8787

Max Act: 3.4247. Min Act: -0.1700

Data Index: 375946 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 3.8787. Min Range: -3.8787

Max Act: 3.4090. Min Act: -0.1700

Data Index: 479385 (C4 (Web Text))

Max Activating Token Index: 261

Text #14

Max Range: 3.8787. Min Range: -3.8787

Max Act: 3.3620. Min Act: -0.1700

Data Index: 203707 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 3.8787. Min Range: -3.8787

Max Act: 3.3777. Min Act: -0.1700

Data Index: 20489 (C4 (Web Text))

Max Activating Token Index: 942

Text #16

Max Range: 3.8787. Min Range: -3.8787

Max Act: 3.3620. Min Act: -0.1700

Data Index: 421302 (C4 (Web Text))

Max Activating Token Index: 906

Text #17

Max Range: 3.8787. Min Range: -3.8787

Max Act: 3.3306. Min Act: -0.1700

Data Index: 730247 (C4 (Web Text))

Max Activating Token Index: 817

Text #18

Max Range: 3.8787. Min Range: -3.8787

Max Act: 3.3620. Min Act: -0.1700

Data Index: 743866 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 3.8787. Min Range: -3.8787

Max Act: 3.2992. Min Act: -0.1700

Data Index: 1189562 (C4 (Web Text))

Max Activating Token Index: 902