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

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

Neuron 375 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: 5.6161. Min Range: -5.6161

Max Act: 5.6161. Min Act: -0.1700

Data Index: 318893 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 5.6161. Min Range: -5.6161

Max Act: 5.4286. Min Act: -0.1700

Data Index: 11318 (C4 (Web Text))

Max Activating Token Index: 625

Text #2

Max Range: 5.6161. Min Range: -5.6161

Max Act: 5.4599. Min Act: -0.1700

Data Index: 1075909 (C4 (Web Text))

Max Activating Token Index: 482

Text #3

Max Range: 5.6161. Min Range: -5.6161

Max Act: 5.4286. Min Act: -0.1700

Data Index: 578696 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 5.6161. Min Range: -5.6161

Max Act: 5.4286. Min Act: -0.1700

Data Index: 641775 (C4 (Web Text))

Max Activating Token Index: 402

Text #5

Max Range: 5.6161. Min Range: -5.6161

Max Act: 5.4286. Min Act: -0.1700

Data Index: 1070545 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 5.6161. Min Range: -5.6161

Max Act: 5.3974. Min Act: -0.1700

Data Index: 1167543 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 5.6161. Min Range: -5.6161

Max Act: 5.3661. Min Act: -0.1700

Data Index: 806513 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 5.6161. Min Range: -5.6161

Max Act: 5.3974. Min Act: -0.1700

Data Index: 594641 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 5.6161. Min Range: -5.6161

Max Act: 5.3974. Min Act: -0.1700

Data Index: 609198 (C4 (Web Text))

Max Activating Token Index: 698

Text #10

Max Range: 5.6161. Min Range: -5.6161

Max Act: 5.3661. Min Act: -0.1700

Data Index: 801554 (C4 (Web Text))

Max Activating Token Index: 323

Text #11

Max Range: 5.6161. Min Range: -5.6161

Max Act: 5.3349. Min Act: -0.1700

Data Index: 62086 (C4 (Web Text))

Max Activating Token Index: 407

Text #12

Max Range: 5.6161. Min Range: -5.6161

Max Act: 5.3661. Min Act: -0.1700

Data Index: 1170711 (C4 (Web Text))

Max Activating Token Index: 572

Text #13

Max Range: 5.6161. Min Range: -5.6161

Max Act: 5.3036. Min Act: -0.1700

Data Index: 508646 (C4 (Web Text))

Max Activating Token Index: 543

Text #14

Max Range: 5.6161. Min Range: -5.6161

Max Act: 5.2724. Min Act: -0.1700

Data Index: 1128145 (C4 (Web Text))

Max Activating Token Index: 427

Text #15

Max Range: 5.6161. Min Range: -5.6161

Max Act: 5.2724. Min Act: -0.1700

Data Index: 347498 (C4 (Web Text))

Max Activating Token Index: 485

Text #16

Max Range: 5.6161. Min Range: -5.6161

Max Act: 5.2724. Min Act: -0.1700

Data Index: 62649 (C4 (Web Text))

Max Activating Token Index: 451

Text #17

Max Range: 5.6161. Min Range: -5.6161

Max Act: 5.3349. Min Act: -0.1700

Data Index: 1247871 (C4 (Web Text))

Max Activating Token Index: 560

Text #18

Max Range: 5.6161. Min Range: -5.6161

Max Act: 5.2724. Min Act: -0.1700

Data Index: 1013451 (C4 (Web Text))

Max Activating Token Index: 557

Text #19

Max Range: 5.6161. Min Range: -5.6161

Max Act: 5.2411. Min Act: -0.1700

Data Index: 48013 (C4 (Web Text))

Max Activating Token Index: 361