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

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

Neuron 1340 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 7.2039. Min Range: -7.2039

Max Act: 7.2039. Min Act: -0.1700

Data Index: 1304216 (C4 (Web Text))

Max Activating Token Index: 281

Text #1

Max Range: 7.2039. Min Range: -7.2039

Max Act: 7.1414. Min Act: -0.1700

Data Index: 1070026 (C4 (Web Text))

Max Activating Token Index: 317

Text #2

Max Range: 7.2039. Min Range: -7.2039

Max Act: 6.8289. Min Act: -0.1700

Data Index: 594651 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 7.2039. Min Range: -7.2039

Max Act: 6.7976. Min Act: -0.1700

Data Index: 521764 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 7.2039. Min Range: -7.2039

Max Act: 6.7351. Min Act: -0.1700

Data Index: 714363 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 7.2039. Min Range: -7.2039

Max Act: 6.6726. Min Act: -0.1700

Data Index: 229217 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 7.2039. Min Range: -7.2039

Max Act: 6.7039. Min Act: -0.1700

Data Index: 714813 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 7.2039. Min Range: -7.2039

Max Act: 6.7664. Min Act: -0.1700

Data Index: 556445 (C4 (Web Text))

Max Activating Token Index: 81

Text #8

Max Range: 7.2039. Min Range: -7.2039

Max Act: 6.7664. Min Act: -0.1700

Data Index: 1073861 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 7.2039. Min Range: -7.2039

Max Act: 6.7039. Min Act: -0.1700

Data Index: 502994 (C4 (Web Text))

Max Activating Token Index: 120

Text #10

Max Range: 7.2039. Min Range: -7.2039

Max Act: 6.6726. Min Act: -0.1700

Data Index: 817625 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 7.2039. Min Range: -7.2039

Max Act: 6.7039. Min Act: -0.1700

Data Index: 197721 (C4 (Web Text))

Max Activating Token Index: 522

Text #12

Max Range: 7.2039. Min Range: -7.2039

Max Act: 6.7039. Min Act: -0.1700

Data Index: 565505 (C4 (Web Text))

Max Activating Token Index: 646

Text #13

Max Range: 7.2039. Min Range: -7.2039

Max Act: 6.7351. Min Act: -0.1700

Data Index: 1202991 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 7.2039. Min Range: -7.2039

Max Act: 6.6414. Min Act: -0.1700

Data Index: 53080 (C4 (Web Text))

Max Activating Token Index: 944

Text #15

Max Range: 7.2039. Min Range: -7.2039

Max Act: 6.6414. Min Act: -0.1700

Data Index: 559144 (C4 (Web Text))

Max Activating Token Index: 667

Text #16

Max Range: 7.2039. Min Range: -7.2039

Max Act: 6.5789. Min Act: -0.1700

Data Index: 132315 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 7.2039. Min Range: -7.2039

Max Act: 6.6101. Min Act: -0.1700

Data Index: 454405 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 7.2039. Min Range: -7.2039

Max Act: 6.5789. Min Act: -0.1700

Data Index: 737101 (C4 (Web Text))

Max Activating Token Index: 548

Text #19

Max Range: 7.2039. Min Range: -7.2039

Max Act: 6.6101. Min Act: -0.1700

Data Index: 559647 (C4 (Web Text))

Max Activating Token Index: 961