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

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

Neuron 1625 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5480. Min Range: -5.5480

Max Act: 5.5480. Min Act: -0.1700

Data Index: 1001175 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 5.5480. Min Range: -5.5480

Max Act: 5.5168. Min Act: -0.1700

Data Index: 1213250 (C4 (Web Text))

Max Activating Token Index: 812

Text #2

Max Range: 5.5480. Min Range: -5.5480

Max Act: 5.4855. Min Act: -0.1700

Data Index: 912706 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 5.5480. Min Range: -5.5480

Max Act: 5.5168. Min Act: -0.1700

Data Index: 63255 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 5.5480. Min Range: -5.5480

Max Act: 5.4543. Min Act: -0.1700

Data Index: 235810 (C4 (Web Text))

Max Activating Token Index: 847

Text #5

Max Range: 5.5480. Min Range: -5.5480

Max Act: 5.5168. Min Act: -0.1700

Data Index: 1328405 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 5.5480. Min Range: -5.5480

Max Act: 5.4543. Min Act: -0.1700

Data Index: 300860 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 5.5480. Min Range: -5.5480

Max Act: 5.4855. Min Act: -0.1700

Data Index: 1007608 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 5.5480. Min Range: -5.5480

Max Act: 5.4543. Min Act: -0.1700

Data Index: 416583 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 5.5480. Min Range: -5.5480

Max Act: 5.4230. Min Act: -0.1700

Data Index: 514571 (C4 (Web Text))

Max Activating Token Index: 664

Text #10

Max Range: 5.5480. Min Range: -5.5480

Max Act: 5.4230. Min Act: -0.1700

Data Index: 394765 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 5.5480. Min Range: -5.5480

Max Act: 5.4230. Min Act: -0.1700

Data Index: 601064 (C4 (Web Text))

Max Activating Token Index: 213

Text #12

Max Range: 5.5480. Min Range: -5.5480

Max Act: 5.3918. Min Act: -0.1700

Data Index: 110531 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 5.5480. Min Range: -5.5480

Max Act: 5.3918. Min Act: -0.1700

Data Index: 716221 (C4 (Web Text))

Max Activating Token Index: 632

Text #14

Max Range: 5.5480. Min Range: -5.5480

Max Act: 5.3605. Min Act: -0.1700

Data Index: 836549 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 5.5480. Min Range: -5.5480

Max Act: 5.3918. Min Act: -0.1700

Data Index: 1211774 (C4 (Web Text))

Max Activating Token Index: 486

Text #16

Max Range: 5.5480. Min Range: -5.5480

Max Act: 5.3605. Min Act: -0.1700

Data Index: 539158 (C4 (Web Text))

Max Activating Token Index: 616

Text #17

Max Range: 5.5480. Min Range: -5.5480

Max Act: 5.3293. Min Act: -0.1700

Data Index: 1101217 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 5.5480. Min Range: -5.5480

Max Act: 5.3293. Min Act: -0.1700

Data Index: 371181 (C4 (Web Text))

Max Activating Token Index: 1006

Text #19

Max Range: 5.5480. Min Range: -5.5480

Max Act: 5.3293. Min Act: -0.1700

Data Index: 79914 (C4 (Web Text))

Max Activating Token Index: 330