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

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

Neuron 673 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: 3.3487. Min Range: -3.3487

Max Act: 3.3487. Min Act: -0.1700

Data Index: 1086494 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 3.3487. Min Range: -3.3487

Max Act: 3.3173. Min Act: -0.1700

Data Index: 65588 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 3.3487. Min Range: -3.3487

Max Act: 3.3016. Min Act: -0.1700

Data Index: 1024885 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 3.3487. Min Range: -3.3487

Max Act: 3.3173. Min Act: -0.1700

Data Index: 449938 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 3.3487. Min Range: -3.3487

Max Act: 3.2859. Min Act: -0.1700

Data Index: 1249956 (C4 (Web Text))

Max Activating Token Index: 380

Text #5

Max Range: 3.3487. Min Range: -3.3487

Max Act: 3.2859. Min Act: -0.1700

Data Index: 493515 (C4 (Web Text))

Max Activating Token Index: 52

Text #6

Max Range: 3.3487. Min Range: -3.3487

Max Act: 3.3016. Min Act: -0.1700

Data Index: 556988 (C4 (Web Text))

Max Activating Token Index: 556

Text #7

Max Range: 3.3487. Min Range: -3.3487

Max Act: 3.3016. Min Act: -0.1700

Data Index: 1236814 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 3.3487. Min Range: -3.3487

Max Act: 3.2545. Min Act: -0.1700

Data Index: 312419 (C4 (Web Text))

Max Activating Token Index: 825

Text #9

Max Range: 3.3487. Min Range: -3.3487

Max Act: 3.2545. Min Act: -0.1700

Data Index: 848306 (C4 (Web Text))

Max Activating Token Index: 9

Text #10

Max Range: 3.3487. Min Range: -3.3487

Max Act: 3.2702. Min Act: -0.1700

Data Index: 482170 (C4 (Web Text))

Max Activating Token Index: 532

Text #11

Max Range: 3.3487. Min Range: -3.3487

Max Act: 3.2388. Min Act: -0.1700

Data Index: 675429 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 3.3487. Min Range: -3.3487

Max Act: 3.2388. Min Act: -0.1700

Data Index: 136153 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 3.3487. Min Range: -3.3487

Max Act: 3.2545. Min Act: -0.1700

Data Index: 1211920 (C4 (Web Text))

Max Activating Token Index: 2

Text #14

Max Range: 3.3487. Min Range: -3.3487

Max Act: 3.2545. Min Act: -0.1700

Data Index: 857954 (C4 (Web Text))

Max Activating Token Index: 921

Text #15

Max Range: 3.3487. Min Range: -3.3487

Max Act: 3.2545. Min Act: -0.1700

Data Index: 395319 (C4 (Web Text))

Max Activating Token Index: 244

Text #16

Max Range: 3.3487. Min Range: -3.3487

Max Act: 3.2859. Min Act: -0.1700

Data Index: 961562 (C4 (Web Text))

Max Activating Token Index: 325

Text #17

Max Range: 3.3487. Min Range: -3.3487

Max Act: 3.2545. Min Act: -0.1700

Data Index: 1142030 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 3.3487. Min Range: -3.3487

Max Act: 3.2545. Min Act: -0.1700

Data Index: 1110638 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 3.3487. Min Range: -3.3487

Max Act: 3.2545. Min Act: -0.1700

Data Index: 1077084 (C4 (Web Text))

Max Activating Token Index: 2