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

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

Neuron 1105 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.4856. Min Range: -5.4856

Max Act: 5.4856. Min Act: -0.1700

Data Index: 842861 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 5.4856. Min Range: -5.4856

Max Act: 5.2356. Min Act: -0.1700

Data Index: 1072705 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 5.4856. Min Range: -5.4856

Max Act: 5.3293. Min Act: -0.1700

Data Index: 557107 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 5.4856. Min Range: -5.4856

Max Act: 5.2981. Min Act: -0.1700

Data Index: 192379 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 5.4856. Min Range: -5.4856

Max Act: 5.2668. Min Act: -0.1700

Data Index: 830006 (C4 (Web Text))

Max Activating Token Index: 628

Text #5

Max Range: 5.4856. Min Range: -5.4856

Max Act: 5.2356. Min Act: -0.1700

Data Index: 1349776 (C4 (Web Text))

Max Activating Token Index: 692

Text #6

Max Range: 5.4856. Min Range: -5.4856

Max Act: 5.2356. Min Act: -0.1700

Data Index: 1356813 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 5.4856. Min Range: -5.4856

Max Act: 5.1418. Min Act: -0.1700

Data Index: 906545 (C4 (Web Text))

Max Activating Token Index: 207

Text #8

Max Range: 5.4856. Min Range: -5.4856

Max Act: 5.0793. Min Act: -0.1700

Data Index: 157849 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 5.4856. Min Range: -5.4856

Max Act: 5.0481. Min Act: -0.1700

Data Index: 72706 (C4 (Web Text))

Max Activating Token Index: 839

Text #10

Max Range: 5.4856. Min Range: -5.4856

Max Act: 5.0793. Min Act: -0.1700

Data Index: 283628 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 5.4856. Min Range: -5.4856

Max Act: 5.0481. Min Act: -0.1700

Data Index: 582899 (C4 (Web Text))

Max Activating Token Index: 801

Text #12

Max Range: 5.4856. Min Range: -5.4856

Max Act: 5.0168. Min Act: -0.1700

Data Index: 413997 (C4 (Web Text))

Max Activating Token Index: 403

Text #13

Max Range: 5.4856. Min Range: -5.4856

Max Act: 5.0168. Min Act: -0.1700

Data Index: 1107481 (C4 (Web Text))

Max Activating Token Index: 576

Text #14

Max Range: 5.4856. Min Range: -5.4856

Max Act: 5.0481. Min Act: -0.1700

Data Index: 1283989 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 5.4856. Min Range: -5.4856

Max Act: 4.9856. Min Act: -0.1700

Data Index: 197940 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 5.4856. Min Range: -5.4856

Max Act: 5.0168. Min Act: -0.1700

Data Index: 155959 (C4 (Web Text))

Max Activating Token Index: 758

Text #17

Max Range: 5.4856. Min Range: -5.4856

Max Act: 4.9543. Min Act: -0.1700

Data Index: 467365 (C4 (Web Text))

Max Activating Token Index: 878

Text #18

Max Range: 5.4856. Min Range: -5.4856

Max Act: 4.9231. Min Act: -0.1700

Data Index: 1176398 (C4 (Web Text))

Max Activating Token Index: 806

Text #19

Max Range: 5.4856. Min Range: -5.4856

Max Act: 4.9231. Min Act: -0.1700

Data Index: 13034 (C4 (Web Text))

Max Activating Token Index: 852