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

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

Neuron 314 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: 3.2554. Min Range: -3.2554

Max Act: 3.2554. Min Act: -0.1700

Data Index: 1284636 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 3.2554. Min Range: -3.2554

Max Act: 3.2397. Min Act: -0.1700

Data Index: 852488 (C4 (Web Text))

Max Activating Token Index: 192

Text #2

Max Range: 3.2554. Min Range: -3.2554

Max Act: 3.2082. Min Act: -0.1700

Data Index: 160877 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 3.2554. Min Range: -3.2554

Max Act: 3.2082. Min Act: -0.1700

Data Index: 1036871 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 3.2554. Min Range: -3.2554

Max Act: 3.1925. Min Act: -0.1700

Data Index: 229580 (C4 (Web Text))

Max Activating Token Index: 802

Text #5

Max Range: 3.2554. Min Range: -3.2554

Max Act: 3.1610. Min Act: -0.1700

Data Index: 38897 (C4 (Web Text))

Max Activating Token Index: 898

Text #6

Max Range: 3.2554. Min Range: -3.2554

Max Act: 3.1610. Min Act: -0.1700

Data Index: 945069 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 3.2554. Min Range: -3.2554

Max Act: 3.1768. Min Act: -0.1700

Data Index: 911635 (C4 (Web Text))

Max Activating Token Index: 367

Text #8

Max Range: 3.2554. Min Range: -3.2554

Max Act: 3.1768. Min Act: -0.1700

Data Index: 382098 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 3.2554. Min Range: -3.2554

Max Act: 3.1768. Min Act: -0.1700

Data Index: 184446 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 3.2554. Min Range: -3.2554

Max Act: 3.1610. Min Act: -0.1700

Data Index: 1523039 (Python Code)

Max Activating Token Index: 615

Text #11

Max Range: 3.2554. Min Range: -3.2554

Max Act: 3.1453. Min Act: -0.1700

Data Index: 1012478 (C4 (Web Text))

Max Activating Token Index: 470

Text #12

Max Range: 3.2554. Min Range: -3.2554

Max Act: 3.1610. Min Act: -0.1700

Data Index: 965879 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 3.2554. Min Range: -3.2554

Max Act: 3.1768. Min Act: -0.1700

Data Index: 602110 (C4 (Web Text))

Max Activating Token Index: 118

Text #14

Max Range: 3.2554. Min Range: -3.2554

Max Act: 3.1453. Min Act: -0.1700

Data Index: 162461 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 3.2554. Min Range: -3.2554

Max Act: 3.1610. Min Act: -0.1700

Data Index: 902570 (C4 (Web Text))

Max Activating Token Index: 104

Text #16

Max Range: 3.2554. Min Range: -3.2554

Max Act: 3.1610. Min Act: -0.1700

Data Index: 324238 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 3.2554. Min Range: -3.2554

Max Act: 3.1610. Min Act: -0.1700

Data Index: 20459 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 3.2554. Min Range: -3.2554

Max Act: 3.1610. Min Act: -0.1700

Data Index: 273885 (C4 (Web Text))

Max Activating Token Index: 241

Text #19

Max Range: 3.2554. Min Range: -3.2554

Max Act: 3.1453. Min Act: -0.1700

Data Index: 638980 (C4 (Web Text))

Max Activating Token Index: 217