Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 71 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.4389. Min Range: -3.4389

Max Act: 3.4389. Min Act: -0.1700

Data Index: 236672 (C4 (Web Text))

Max Activating Token Index: 70

Text #1

Max Range: 3.4389. Min Range: -3.4389

Max Act: 3.2663. Min Act: -0.1700

Data Index: 119164 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 3.4389. Min Range: -3.4389

Max Act: 3.2349. Min Act: -0.1700

Data Index: 1274230 (C4 (Web Text))

Max Activating Token Index: 485

Text #3

Max Range: 3.4389. Min Range: -3.4389

Max Act: 3.2349. Min Act: -0.1700

Data Index: 198566 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 3.4389. Min Range: -3.4389

Max Act: 3.2191. Min Act: -0.1700

Data Index: 736635 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 3.4389. Min Range: -3.4389

Max Act: 3.1877. Min Act: -0.1700

Data Index: 937829 (C4 (Web Text))

Max Activating Token Index: 626

Text #6

Max Range: 3.4389. Min Range: -3.4389

Max Act: 3.1877. Min Act: -0.1700

Data Index: 259460 (C4 (Web Text))

Max Activating Token Index: 1011

Text #7

Max Range: 3.4389. Min Range: -3.4389

Max Act: 3.1404. Min Act: -0.1700

Data Index: 886782 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 3.4389. Min Range: -3.4389

Max Act: 3.1719. Min Act: -0.1700

Data Index: 922903 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 3.4389. Min Range: -3.4389

Max Act: 3.1562. Min Act: -0.1700

Data Index: 355781 (C4 (Web Text))

Max Activating Token Index: 365

Text #10

Max Range: 3.4389. Min Range: -3.4389

Max Act: 3.1562. Min Act: -0.1700

Data Index: 842912 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 3.4389. Min Range: -3.4389

Max Act: 3.1562. Min Act: -0.1700

Data Index: 41178 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 3.4389. Min Range: -3.4389

Max Act: 3.1247. Min Act: -0.1700

Data Index: 864001 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 3.4389. Min Range: -3.4389

Max Act: 3.1404. Min Act: -0.1700

Data Index: 888241 (C4 (Web Text))

Max Activating Token Index: 483

Text #14

Max Range: 3.4389. Min Range: -3.4389

Max Act: 3.1404. Min Act: -0.1700

Data Index: 222327 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 3.4389. Min Range: -3.4389

Max Act: 3.1247. Min Act: -0.1700

Data Index: 811864 (C4 (Web Text))

Max Activating Token Index: 782

Text #16

Max Range: 3.4389. Min Range: -3.4389

Max Act: 3.1247. Min Act: -0.1700

Data Index: 356755 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 3.4389. Min Range: -3.4389

Max Act: 3.1247. Min Act: -0.1700

Data Index: 187622 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 3.4389. Min Range: -3.4389

Max Act: 3.1247. Min Act: -0.1700

Data Index: 742685 (C4 (Web Text))

Max Activating Token Index: 504

Text #19

Max Range: 3.4389. Min Range: -3.4389

Max Act: 3.1247. Min Act: -0.1700

Data Index: 908432 (C4 (Web Text))

Max Activating Token Index: 462