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

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

Neuron 489 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: 1.9105. Min Range: -1.9105

Max Act: 1.9105. Min Act: -0.1700

Data Index: 1560403 (Python Code)

Max Activating Token Index: 976

Text #1

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.8764. Min Act: -0.1700

Data Index: 196323 (C4 (Web Text))

Max Activating Token Index: 379

Text #2

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.8935. Min Act: -0.1700

Data Index: 1376063 (Python Code)

Max Activating Token Index: 103

Text #3

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.8422. Min Act: -0.1700

Data Index: 1408954 (Python Code)

Max Activating Token Index: 175

Text #4

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.8336. Min Act: -0.1700

Data Index: 1235438 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.8422. Min Act: -0.1700

Data Index: 1571404 (Python Code)

Max Activating Token Index: 729

Text #6

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.8422. Min Act: -0.1700

Data Index: 678249 (C4 (Web Text))

Max Activating Token Index: 449

Text #7

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.8336. Min Act: -0.1700

Data Index: 784477 (C4 (Web Text))

Max Activating Token Index: 125

Text #8

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.8251. Min Act: -0.1700

Data Index: 1335601 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.8251. Min Act: -0.1700

Data Index: 425010 (C4 (Web Text))

Max Activating Token Index: 162

Text #10

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.7993. Min Act: -0.1700

Data Index: 1208259 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.7907. Min Act: -0.1700

Data Index: 1503087 (Python Code)

Max Activating Token Index: 687

Text #12

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.8165. Min Act: -0.1700

Data Index: 1396553 (Python Code)

Max Activating Token Index: 212

Text #13

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.8165. Min Act: -0.1700

Data Index: 1454303 (Python Code)

Max Activating Token Index: 191

Text #14

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.8079. Min Act: -0.1700

Data Index: 1577820 (Python Code)

Max Activating Token Index: 623

Text #15

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.8079. Min Act: -0.1700

Data Index: 1449736 (Python Code)

Max Activating Token Index: 156

Text #16

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.8165. Min Act: -0.1700

Data Index: 1381426 (Python Code)

Max Activating Token Index: 192

Text #17

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.8165. Min Act: -0.1700

Data Index: 765722 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.8165. Min Act: -0.1700

Data Index: 1184054 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 1.9105. Min Range: -1.9105

Max Act: 1.8079. Min Act: -0.1700

Data Index: 1363857 (Python Code)

Max Activating Token Index: 239