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

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

Neuron 494 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: 3.8298. Min Range: -3.8298

Max Act: 3.8298. Min Act: -0.1700

Data Index: 263807 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 3.8298. Min Range: -3.8298

Max Act: 3.6421. Min Act: -0.1700

Data Index: 614622 (C4 (Web Text))

Max Activating Token Index: 910

Text #2

Max Range: 3.8298. Min Range: -3.8298

Max Act: 3.5795. Min Act: -0.1700

Data Index: 1201811 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 3.8298. Min Range: -3.8298

Max Act: 3.5638. Min Act: -0.1700

Data Index: 190767 (C4 (Web Text))

Max Activating Token Index: 806

Text #4

Max Range: 3.8298. Min Range: -3.8298

Max Act: 3.5325. Min Act: -0.1700

Data Index: 497642 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 3.8298. Min Range: -3.8298

Max Act: 3.5168. Min Act: -0.1700

Data Index: 480972 (C4 (Web Text))

Max Activating Token Index: 592

Text #6

Max Range: 3.8298. Min Range: -3.8298

Max Act: 3.5011. Min Act: -0.1700

Data Index: 1191866 (C4 (Web Text))

Max Activating Token Index: 527

Text #7

Max Range: 3.8298. Min Range: -3.8298

Max Act: 3.4698. Min Act: -0.1700

Data Index: 872054 (C4 (Web Text))

Max Activating Token Index: 389

Text #8

Max Range: 3.8298. Min Range: -3.8298

Max Act: 3.4698. Min Act: -0.1700

Data Index: 967382 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 3.8298. Min Range: -3.8298

Max Act: 3.4384. Min Act: -0.1700

Data Index: 82827 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 3.8298. Min Range: -3.8298

Max Act: 3.3914. Min Act: -0.1700

Data Index: 1057204 (C4 (Web Text))

Max Activating Token Index: 803

Text #11

Max Range: 3.8298. Min Range: -3.8298

Max Act: 3.4071. Min Act: -0.1700

Data Index: 214376 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 3.8298. Min Range: -3.8298

Max Act: 3.4071. Min Act: -0.1700

Data Index: 707950 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 3.8298. Min Range: -3.8298

Max Act: 3.3129. Min Act: -0.1700

Data Index: 253660 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 3.8298. Min Range: -3.8298

Max Act: 3.3286. Min Act: -0.1700

Data Index: 646863 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 3.8298. Min Range: -3.8298

Max Act: 3.3129. Min Act: -0.1700

Data Index: 1356648 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 3.8298. Min Range: -3.8298

Max Act: 3.3286. Min Act: -0.1700

Data Index: 88589 (C4 (Web Text))

Max Activating Token Index: 985

Text #17

Max Range: 3.8298. Min Range: -3.8298

Max Act: 3.2972. Min Act: -0.1700

Data Index: 403198 (C4 (Web Text))

Max Activating Token Index: 801

Text #18

Max Range: 3.8298. Min Range: -3.8298

Max Act: 3.2972. Min Act: -0.1700

Data Index: 57 (C4 (Web Text))

Max Activating Token Index: 639

Text #19

Max Range: 3.8298. Min Range: -3.8298

Max Act: 3.2815. Min Act: -0.1700

Data Index: 700802 (C4 (Web Text))

Max Activating Token Index: 22