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

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

Neuron 250 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2712. Min Range: -5.2712

Max Act: 5.2712. Min Act: -0.1700

Data Index: 486732 (C4 (Web Text))

Max Activating Token Index: 583

Text #1

Max Range: 5.2712. Min Range: -5.2712

Max Act: 5.2400. Min Act: -0.1700

Data Index: 8929 (C4 (Web Text))

Max Activating Token Index: 495

Text #2

Max Range: 5.2712. Min Range: -5.2712

Max Act: 5.1462. Min Act: -0.1700

Data Index: 18378 (C4 (Web Text))

Max Activating Token Index: 380

Text #3

Max Range: 5.2712. Min Range: -5.2712

Max Act: 5.1462. Min Act: -0.1700

Data Index: 980622 (C4 (Web Text))

Max Activating Token Index: 678

Text #4

Max Range: 5.2712. Min Range: -5.2712

Max Act: 5.2400. Min Act: -0.1700

Data Index: 246786 (C4 (Web Text))

Max Activating Token Index: 438

Text #5

Max Range: 5.2712. Min Range: -5.2712

Max Act: 5.0837. Min Act: -0.1700

Data Index: 478271 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 5.2712. Min Range: -5.2712

Max Act: 5.1150. Min Act: -0.1700

Data Index: 272921 (C4 (Web Text))

Max Activating Token Index: 626

Text #7

Max Range: 5.2712. Min Range: -5.2712

Max Act: 5.0525. Min Act: -0.1700

Data Index: 724291 (C4 (Web Text))

Max Activating Token Index: 381

Text #8

Max Range: 5.2712. Min Range: -5.2712

Max Act: 4.9900. Min Act: -0.1700

Data Index: 141063 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 5.2712. Min Range: -5.2712

Max Act: 5.0212. Min Act: -0.1700

Data Index: 1294865 (C4 (Web Text))

Max Activating Token Index: 133

Text #10

Max Range: 5.2712. Min Range: -5.2712

Max Act: 5.0212. Min Act: -0.1700

Data Index: 897926 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 5.2712. Min Range: -5.2712

Max Act: 4.9900. Min Act: -0.1700

Data Index: 1128054 (C4 (Web Text))

Max Activating Token Index: 202

Text #12

Max Range: 5.2712. Min Range: -5.2712

Max Act: 5.0212. Min Act: -0.1700

Data Index: 881922 (C4 (Web Text))

Max Activating Token Index: 616

Text #13

Max Range: 5.2712. Min Range: -5.2712

Max Act: 4.8962. Min Act: -0.1700

Data Index: 552215 (C4 (Web Text))

Max Activating Token Index: 993

Text #14

Max Range: 5.2712. Min Range: -5.2712

Max Act: 4.8962. Min Act: -0.1700

Data Index: 1095623 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 5.2712. Min Range: -5.2712

Max Act: 4.8337. Min Act: -0.1700

Data Index: 496199 (C4 (Web Text))

Max Activating Token Index: 906

Text #16

Max Range: 5.2712. Min Range: -5.2712

Max Act: 4.8025. Min Act: -0.1700

Data Index: 1125538 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 5.2712. Min Range: -5.2712

Max Act: 4.8025. Min Act: -0.1700

Data Index: 130441 (C4 (Web Text))

Max Activating Token Index: 368

Text #18

Max Range: 5.2712. Min Range: -5.2712

Max Act: 4.8025. Min Act: -0.1700

Data Index: 518671 (C4 (Web Text))

Max Activating Token Index: 760

Text #19

Max Range: 5.2712. Min Range: -5.2712

Max Act: 4.8337. Min Act: -0.1700

Data Index: 1089183 (C4 (Web Text))

Max Activating Token Index: 567