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

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

Neuron 86 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: 3.3165. Min Range: -3.3165

Max Act: 3.3165. Min Act: -0.1700

Data Index: 1471746 (Python Code)

Max Activating Token Index: 476

Text #1

Max Range: 3.3165. Min Range: -3.3165

Max Act: 3.3165. Min Act: -0.1700

Data Index: 1417102 (Python Code)

Max Activating Token Index: 59

Text #2

Max Range: 3.3165. Min Range: -3.3165

Max Act: 3.3008. Min Act: -0.1700

Data Index: 1419959 (Python Code)

Max Activating Token Index: 387

Text #3

Max Range: 3.3165. Min Range: -3.3165

Max Act: 3.2380. Min Act: -0.1700

Data Index: 1371781 (Python Code)

Max Activating Token Index: 369

Text #4

Max Range: 3.3165. Min Range: -3.3165

Max Act: 3.2223. Min Act: -0.1700

Data Index: 1382311 (Python Code)

Max Activating Token Index: 153

Text #5

Max Range: 3.3165. Min Range: -3.3165

Max Act: 3.2065. Min Act: -0.1700

Data Index: 1632197 (Python Code)

Max Activating Token Index: 884

Text #6

Max Range: 3.3165. Min Range: -3.3165

Max Act: 3.1751. Min Act: -0.1700

Data Index: 1421051 (Python Code)

Max Activating Token Index: 130

Text #7

Max Range: 3.3165. Min Range: -3.3165

Max Act: 3.1593. Min Act: -0.1700

Data Index: 1528383 (Python Code)

Max Activating Token Index: 183

Text #8

Max Range: 3.3165. Min Range: -3.3165

Max Act: 3.1593. Min Act: -0.1700

Data Index: 1390538 (Python Code)

Max Activating Token Index: 140

Text #9

Max Range: 3.3165. Min Range: -3.3165

Max Act: 3.1278. Min Act: -0.1700

Data Index: 113841 (C4 (Web Text))

Max Activating Token Index: 362

Text #10

Max Range: 3.3165. Min Range: -3.3165

Max Act: 3.1278. Min Act: -0.1700

Data Index: 1569331 (Python Code)

Max Activating Token Index: 75

Text #11

Max Range: 3.3165. Min Range: -3.3165

Max Act: 3.1436. Min Act: -0.1700

Data Index: 858456 (C4 (Web Text))

Max Activating Token Index: 582

Text #12

Max Range: 3.3165. Min Range: -3.3165

Max Act: 3.1121. Min Act: -0.1700

Data Index: 425612 (C4 (Web Text))

Max Activating Token Index: 851

Text #13

Max Range: 3.3165. Min Range: -3.3165

Max Act: 3.1121. Min Act: -0.1700

Data Index: 267405 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 3.3165. Min Range: -3.3165

Max Act: 3.1121. Min Act: -0.1700

Data Index: 163510 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 3.3165. Min Range: -3.3165

Max Act: 3.1121. Min Act: -0.1700

Data Index: 117098 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 3.3165. Min Range: -3.3165

Max Act: 3.0963. Min Act: -0.1699

Data Index: 1521540 (Python Code)

Max Activating Token Index: 326

Text #17

Max Range: 3.3165. Min Range: -3.3165

Max Act: 3.0805. Min Act: -0.1700

Data Index: 1593026 (Python Code)

Max Activating Token Index: 202

Text #18

Max Range: 3.3165. Min Range: -3.3165

Max Act: 3.0963. Min Act: -0.1700

Data Index: 600351 (C4 (Web Text))

Max Activating Token Index: 466

Text #19

Max Range: 3.3165. Min Range: -3.3165

Max Act: 3.0647. Min Act: -0.1700

Data Index: 1496822 (Python Code)

Max Activating Token Index: 912