Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1695 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.4299. Min Range: -3.4299

Max Act: 3.4299. Min Act: -0.1700

Data Index: 806369 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 3.4299. Min Range: -3.4299

Max Act: 3.3986. Min Act: -0.1700

Data Index: 166322 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 3.4299. Min Range: -3.4299

Max Act: 3.3829. Min Act: -0.1700

Data Index: 260127 (C4 (Web Text))

Max Activating Token Index: 393

Text #3

Max Range: 3.4299. Min Range: -3.4299

Max Act: 3.3358. Min Act: -0.1700

Data Index: 471059 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 3.4299. Min Range: -3.4299

Max Act: 3.3201. Min Act: -0.1700

Data Index: 959257 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 3.4299. Min Range: -3.4299

Max Act: 3.3201. Min Act: -0.1700

Data Index: 1188994 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 3.4299. Min Range: -3.4299

Max Act: 3.2887. Min Act: -0.1700

Data Index: 883758 (C4 (Web Text))

Max Activating Token Index: 714

Text #7

Max Range: 3.4299. Min Range: -3.4299

Max Act: 3.2730. Min Act: -0.1700

Data Index: 1344465 (C4 (Web Text))

Max Activating Token Index: 214

Text #8

Max Range: 3.4299. Min Range: -3.4299

Max Act: 3.2573. Min Act: -0.1700

Data Index: 1047004 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 3.4299. Min Range: -3.4299

Max Act: 3.2415. Min Act: -0.1700

Data Index: 239522 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 3.4299. Min Range: -3.4299

Max Act: 3.2415. Min Act: -0.1700

Data Index: 1079164 (C4 (Web Text))

Max Activating Token Index: 852

Text #11

Max Range: 3.4299. Min Range: -3.4299

Max Act: 3.2573. Min Act: -0.1700

Data Index: 858485 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 3.4299. Min Range: -3.4299

Max Act: 3.2415. Min Act: -0.1700

Data Index: 1332984 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 3.4299. Min Range: -3.4299

Max Act: 3.2573. Min Act: -0.1700

Data Index: 1005760 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 3.4299. Min Range: -3.4299

Max Act: 3.2415. Min Act: -0.1700

Data Index: 676116 (C4 (Web Text))

Max Activating Token Index: 608

Text #15

Max Range: 3.4299. Min Range: -3.4299

Max Act: 3.2258. Min Act: -0.1700

Data Index: 24262 (C4 (Web Text))

Max Activating Token Index: 946

Text #16

Max Range: 3.4299. Min Range: -3.4299

Max Act: 3.2258. Min Act: -0.1700

Data Index: 648078 (C4 (Web Text))

Max Activating Token Index: 25

Text #17

Max Range: 3.4299. Min Range: -3.4299

Max Act: 3.2258. Min Act: -0.1700

Data Index: 492279 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 3.4299. Min Range: -3.4299

Max Act: 3.2101. Min Act: -0.1700

Data Index: 1151613 (C4 (Web Text))

Max Activating Token Index: 350

Text #19

Max Range: 3.4299. Min Range: -3.4299

Max Act: 3.1944. Min Act: -0.1700

Data Index: 1036308 (C4 (Web Text))

Max Activating Token Index: 264