Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 306 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 6.1887. Min Range: -6.1887

Max Act: 6.1887. Min Act: -0.1700

Data Index: 496918 (C4 (Web Text))

Max Activating Token Index: 762

Text #1

Max Range: 6.1887. Min Range: -6.1887

Max Act: 6.1805. Min Act: -0.1633

Data Index: 810742 (C4 (Web Text))

Max Activating Token Index: 527

Text #2

Max Range: 6.1887. Min Range: -6.1887

Max Act: 6.1065. Min Act: -0.1700

Data Index: 765923 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 6.1887. Min Range: -6.1887

Max Act: 6.1123. Min Act: -0.1700

Data Index: 1020519 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 6.1887. Min Range: -6.1887

Max Act: 6.0357. Min Act: -0.1700

Data Index: 46731 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 6.1887. Min Range: -6.1887

Max Act: 5.9943. Min Act: -0.1700

Data Index: 830881 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 6.1887. Min Range: -6.1887

Max Act: 5.9946. Min Act: -0.1633

Data Index: 1058875 (C4 (Web Text))

Max Activating Token Index: 133

Text #7

Max Range: 6.1887. Min Range: -6.1887

Max Act: 5.9294. Min Act: -0.1700

Data Index: 716435 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 6.1887. Min Range: -6.1887

Max Act: 5.8792. Min Act: -0.1700

Data Index: 1087958 (C4 (Web Text))

Max Activating Token Index: 491

Text #9

Max Range: 6.1887. Min Range: -6.1887

Max Act: 5.8524. Min Act: -0.1700

Data Index: 1060076 (C4 (Web Text))

Max Activating Token Index: 761

Text #10

Max Range: 6.1887. Min Range: -6.1887

Max Act: 5.8408. Min Act: -0.1700

Data Index: 109577 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 6.1887. Min Range: -6.1887

Max Act: 5.8632. Min Act: -0.1700

Data Index: 944130 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 6.1887. Min Range: -6.1887

Max Act: 5.8474. Min Act: -0.1700

Data Index: 114751 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 6.1887. Min Range: -6.1887

Max Act: 5.7950. Min Act: -0.1700

Data Index: 33439 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 6.1887. Min Range: -6.1887

Max Act: 5.8226. Min Act: -0.1633

Data Index: 1132673 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 6.1887. Min Range: -6.1887

Max Act: 5.8168. Min Act: -0.1699

Data Index: 36420 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 6.1887. Min Range: -6.1887

Max Act: 5.8195. Min Act: -0.1700

Data Index: 1712 (C4 (Web Text))

Max Activating Token Index: 880

Text #17

Max Range: 6.1887. Min Range: -6.1887

Max Act: 5.8048. Min Act: -0.1698

Data Index: 636542 (C4 (Web Text))

Max Activating Token Index: 360

Text #18

Max Range: 6.1887. Min Range: -6.1887

Max Act: 5.7703. Min Act: -0.1700

Data Index: 425565 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 6.1887. Min Range: -6.1887

Max Act: 5.7824. Min Act: -0.1700

Data Index: 1032484 (C4 (Web Text))

Max Activating Token Index: 245