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

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

Neuron 267 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: 4.8728. Min Range: -4.8728

Max Act: 4.8728. Min Act: -0.1700

Data Index: 936062 (C4 (Web Text))

Max Activating Token Index: 877

Text #1

Max Range: 4.8728. Min Range: -4.8728

Max Act: 4.6588. Min Act: -0.1700

Data Index: 469826 (C4 (Web Text))

Max Activating Token Index: 451

Text #2

Max Range: 4.8728. Min Range: -4.8728

Max Act: 4.6296. Min Act: -0.1700

Data Index: 1109367 (C4 (Web Text))

Max Activating Token Index: 955

Text #3

Max Range: 4.8728. Min Range: -4.8728

Max Act: 4.6256. Min Act: -0.1700

Data Index: 208784 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 4.8728. Min Range: -4.8728

Max Act: 4.5740. Min Act: -0.1700

Data Index: 1282667 (C4 (Web Text))

Max Activating Token Index: 460

Text #5

Max Range: 4.8728. Min Range: -4.8728

Max Act: 4.5534. Min Act: -0.1700

Data Index: 1413300 (Python Code)

Max Activating Token Index: 992

Text #6

Max Range: 4.8728. Min Range: -4.8728

Max Act: 4.5466. Min Act: -0.1700

Data Index: 290338 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 4.8728. Min Range: -4.8728

Max Act: 4.5521. Min Act: -0.1700

Data Index: 98833 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 4.8728. Min Range: -4.8728

Max Act: 4.5280. Min Act: -0.1700

Data Index: 963712 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 4.8728. Min Range: -4.8728

Max Act: 4.5256. Min Act: -0.1700

Data Index: 1524368 (Python Code)

Max Activating Token Index: 548

Text #10

Max Range: 4.8728. Min Range: -4.8728

Max Act: 4.5215. Min Act: -0.1700

Data Index: 1154046 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 4.8728. Min Range: -4.8728

Max Act: 4.5259. Min Act: -0.1700

Data Index: 1095780 (C4 (Web Text))

Max Activating Token Index: 902

Text #12

Max Range: 4.8728. Min Range: -4.8728

Max Act: 4.5210. Min Act: -0.1700

Data Index: 131391 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 4.8728. Min Range: -4.8728

Max Act: 4.4979. Min Act: -0.1700

Data Index: 2848 (C4 (Web Text))

Max Activating Token Index: 413

Text #14

Max Range: 4.8728. Min Range: -4.8728

Max Act: 4.5011. Min Act: -0.1700

Data Index: 589707 (C4 (Web Text))

Max Activating Token Index: 999

Text #15

Max Range: 4.8728. Min Range: -4.8728

Max Act: 4.4720. Min Act: -0.1700

Data Index: 553080 (C4 (Web Text))

Max Activating Token Index: 296

Text #16

Max Range: 4.8728. Min Range: -4.8728

Max Act: 4.4892. Min Act: -0.1700

Data Index: 142942 (C4 (Web Text))

Max Activating Token Index: 201

Text #17

Max Range: 4.8728. Min Range: -4.8728

Max Act: 4.5003. Min Act: -0.1700

Data Index: 1265009 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 4.8728. Min Range: -4.8728

Max Act: 4.4699. Min Act: -0.1700

Data Index: 596295 (C4 (Web Text))

Max Activating Token Index: 693

Text #19

Max Range: 4.8728. Min Range: -4.8728

Max Act: 4.4586. Min Act: -0.1700

Data Index: 213895 (C4 (Web Text))

Max Activating Token Index: 651