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

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

Neuron 738 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: 5.4215. Min Range: -5.4215

Max Act: 5.4215. Min Act: -0.1700

Data Index: 753839 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 5.4215. Min Range: -5.4215

Max Act: 5.3902. Min Act: -0.1700

Data Index: 430362 (C4 (Web Text))

Max Activating Token Index: 246

Text #2

Max Range: 5.4215. Min Range: -5.4215

Max Act: 5.4215. Min Act: -0.1700

Data Index: 222948 (C4 (Web Text))

Max Activating Token Index: 822

Text #3

Max Range: 5.4215. Min Range: -5.4215

Max Act: 5.4215. Min Act: -0.1700

Data Index: 1303859 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 5.4215. Min Range: -5.4215

Max Act: 5.3902. Min Act: -0.1700

Data Index: 1318630 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 5.4215. Min Range: -5.4215

Max Act: 5.3902. Min Act: -0.1700

Data Index: 547902 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 5.4215. Min Range: -5.4215

Max Act: 5.3902. Min Act: -0.1700

Data Index: 32031 (C4 (Web Text))

Max Activating Token Index: 294

Text #7

Max Range: 5.4215. Min Range: -5.4215

Max Act: 5.4215. Min Act: -0.1700

Data Index: 492126 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 5.4215. Min Range: -5.4215

Max Act: 5.4215. Min Act: -0.1700

Data Index: 107759 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 5.4215. Min Range: -5.4215

Max Act: 5.3902. Min Act: -0.1700

Data Index: 678979 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 5.4215. Min Range: -5.4215

Max Act: 5.4215. Min Act: -0.1700

Data Index: 832943 (C4 (Web Text))

Max Activating Token Index: 610

Text #11

Max Range: 5.4215. Min Range: -5.4215

Max Act: 5.3902. Min Act: -0.1700

Data Index: 1088619 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 5.4215. Min Range: -5.4215

Max Act: 5.3902. Min Act: -0.1700

Data Index: 300108 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 5.4215. Min Range: -5.4215

Max Act: 5.3590. Min Act: -0.1700

Data Index: 107728 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 5.4215. Min Range: -5.4215

Max Act: 5.3590. Min Act: -0.1700

Data Index: 662259 (C4 (Web Text))

Max Activating Token Index: 699

Text #15

Max Range: 5.4215. Min Range: -5.4215

Max Act: 5.3902. Min Act: -0.1700

Data Index: 30912 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 5.4215. Min Range: -5.4215

Max Act: 5.3590. Min Act: -0.1700

Data Index: 977056 (C4 (Web Text))

Max Activating Token Index: 705

Text #17

Max Range: 5.4215. Min Range: -5.4215

Max Act: 5.3590. Min Act: -0.1700

Data Index: 391594 (C4 (Web Text))

Max Activating Token Index: 938

Text #18

Max Range: 5.4215. Min Range: -5.4215

Max Act: 5.3277. Min Act: -0.1700

Data Index: 357801 (C4 (Web Text))

Max Activating Token Index: 428

Text #19

Max Range: 5.4215. Min Range: -5.4215

Max Act: 5.3902. Min Act: -0.1700

Data Index: 1204040 (C4 (Web Text))

Max Activating Token Index: 620