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

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

Neuron 931 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5885. Min Range: -3.5885

Max Act: 3.5885. Min Act: -0.1700

Data Index: 1211189 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 3.5885. Min Range: -3.5885

Max Act: 3.5572. Min Act: -0.1700

Data Index: 1233587 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 3.5885. Min Range: -3.5885

Max Act: 3.5415. Min Act: -0.1700

Data Index: 1447673 (Python Code)

Max Activating Token Index: 19

Text #3

Max Range: 3.5885. Min Range: -3.5885

Max Act: 3.5415. Min Act: -0.1700

Data Index: 1244457 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 3.5885. Min Range: -3.5885

Max Act: 3.4632. Min Act: -0.1700

Data Index: 571059 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 3.5885. Min Range: -3.5885

Max Act: 3.4632. Min Act: -0.1700

Data Index: 875748 (C4 (Web Text))

Max Activating Token Index: 577

Text #6

Max Range: 3.5885. Min Range: -3.5885

Max Act: 3.4475. Min Act: -0.1700

Data Index: 1003870 (C4 (Web Text))

Max Activating Token Index: 347

Text #7

Max Range: 3.5885. Min Range: -3.5885

Max Act: 3.4318. Min Act: -0.1700

Data Index: 716836 (C4 (Web Text))

Max Activating Token Index: 246

Text #8

Max Range: 3.5885. Min Range: -3.5885

Max Act: 3.4789. Min Act: -0.1700

Data Index: 1630532 (Python Code)

Max Activating Token Index: 53

Text #9

Max Range: 3.5885. Min Range: -3.5885

Max Act: 3.5259. Min Act: -0.1700

Data Index: 1397542 (Python Code)

Max Activating Token Index: 16

Text #10

Max Range: 3.5885. Min Range: -3.5885

Max Act: 3.4475. Min Act: -0.1700

Data Index: 599197 (C4 (Web Text))

Max Activating Token Index: 181

Text #11

Max Range: 3.5885. Min Range: -3.5885

Max Act: 3.4005. Min Act: -0.1700

Data Index: 135074 (C4 (Web Text))

Max Activating Token Index: 847

Text #12

Max Range: 3.5885. Min Range: -3.5885

Max Act: 3.4475. Min Act: -0.1700

Data Index: 1111735 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 3.5885. Min Range: -3.5885

Max Act: 3.4475. Min Act: -0.1700

Data Index: 938698 (C4 (Web Text))

Max Activating Token Index: 996

Text #14

Max Range: 3.5885. Min Range: -3.5885

Max Act: 3.4318. Min Act: -0.1699

Data Index: 445353 (C4 (Web Text))

Max Activating Token Index: 281

Text #15

Max Range: 3.5885. Min Range: -3.5885

Max Act: 3.4162. Min Act: -0.1700

Data Index: 1480104 (Python Code)

Max Activating Token Index: 15

Text #16

Max Range: 3.5885. Min Range: -3.5885

Max Act: 3.4005. Min Act: -0.1700

Data Index: 1300038 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 3.5885. Min Range: -3.5885

Max Act: 3.4162. Min Act: -0.1700

Data Index: 1209977 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 3.5885. Min Range: -3.5885

Max Act: 3.3848. Min Act: -0.1699

Data Index: 337611 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 3.5885. Min Range: -3.5885

Max Act: 3.4005. Min Act: -0.1700

Data Index: 1293174 (C4 (Web Text))

Max Activating Token Index: 685