Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1909 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.7931. Min Act: -0.1700

Data Index: 1617712 (Python Code)

Max Activating Token Index: 299

Text #1

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.7931. Min Act: -0.1700

Data Index: 1518112 (Python Code)

Max Activating Token Index: 77

Text #2

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.7619. Min Act: -0.1700

Data Index: 615764 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.7931. Min Act: -0.1700

Data Index: 1458577 (Python Code)

Max Activating Token Index: 599

Text #4

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.7619. Min Act: -0.1700

Data Index: 1519962 (Python Code)

Max Activating Token Index: 35

Text #5

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.7306. Min Act: -0.1700

Data Index: 1462536 (Python Code)

Max Activating Token Index: 914

Text #6

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.7775. Min Act: -0.1700

Data Index: 1535074 (Python Code)

Max Activating Token Index: 758

Text #7

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.6993. Min Act: -0.1700

Data Index: 565123 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.7306. Min Act: -0.1700

Data Index: 1621551 (Python Code)

Max Activating Token Index: 148

Text #9

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.7462. Min Act: -0.1700

Data Index: 582802 (C4 (Web Text))

Max Activating Token Index: 475

Text #10

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.7149. Min Act: -0.1700

Data Index: 1440486 (Python Code)

Max Activating Token Index: 178

Text #11

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.7149. Min Act: -0.1700

Data Index: 826133 (C4 (Web Text))

Max Activating Token Index: 173

Text #12

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.6993. Min Act: -0.1700

Data Index: 1483874 (Python Code)

Max Activating Token Index: 51

Text #13

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.6836. Min Act: -0.1700

Data Index: 1555492 (Python Code)

Max Activating Token Index: 246

Text #14

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.6523. Min Act: -0.1700

Data Index: 1365408 (Python Code)

Max Activating Token Index: 910

Text #15

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.6836. Min Act: -0.1700

Data Index: 1219069 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.6993. Min Act: -0.1700

Data Index: 1235351 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.6680. Min Act: -0.1700

Data Index: 1594882 (Python Code)

Max Activating Token Index: 274

Text #18

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.6680. Min Act: -0.1700

Data Index: 1620068 (Python Code)

Max Activating Token Index: 692

Text #19

Max Range: 3.7931. Min Range: -3.7931

Max Act: 3.6680. Min Act: -0.1700

Data Index: 1405844 (Python Code)

Max Activating Token Index: 519