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

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

Neuron 1250 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8866. Min Range: -3.8866

Max Act: 3.8866. Min Act: -0.1700

Data Index: 880402 (C4 (Web Text))

Max Activating Token Index: 532

Text #1

Max Range: 3.8866. Min Range: -3.8866

Max Act: 3.8240. Min Act: -0.1700

Data Index: 510418 (C4 (Web Text))

Max Activating Token Index: 512

Text #2

Max Range: 3.8866. Min Range: -3.8866

Max Act: 3.7927. Min Act: -0.1700

Data Index: 349407 (C4 (Web Text))

Max Activating Token Index: 635

Text #3

Max Range: 3.8866. Min Range: -3.8866

Max Act: 3.7927. Min Act: -0.1700

Data Index: 848870 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 3.8866. Min Range: -3.8866

Max Act: 3.7301. Min Act: -0.1700

Data Index: 1070139 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 3.8866. Min Range: -3.8866

Max Act: 3.6989. Min Act: -0.1700

Data Index: 261308 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 3.8866. Min Range: -3.8866

Max Act: 3.7927. Min Act: -0.1700

Data Index: 981291 (C4 (Web Text))

Max Activating Token Index: 766

Text #7

Max Range: 3.8866. Min Range: -3.8866

Max Act: 3.7301. Min Act: -0.1700

Data Index: 461584 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 3.8866. Min Range: -3.8866

Max Act: 3.6989. Min Act: -0.1700

Data Index: 1036899 (C4 (Web Text))

Max Activating Token Index: 614

Text #9

Max Range: 3.8866. Min Range: -3.8866

Max Act: 3.7614. Min Act: -0.1700

Data Index: 724407 (C4 (Web Text))

Max Activating Token Index: 284

Text #10

Max Range: 3.8866. Min Range: -3.8866

Max Act: 3.6989. Min Act: -0.1700

Data Index: 803677 (C4 (Web Text))

Max Activating Token Index: 902

Text #11

Max Range: 3.8866. Min Range: -3.8866

Max Act: 3.7614. Min Act: -0.1700

Data Index: 1227831 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 3.8866. Min Range: -3.8866

Max Act: 3.6989. Min Act: -0.1700

Data Index: 309912 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 3.8866. Min Range: -3.8866

Max Act: 3.6676. Min Act: -0.1700

Data Index: 792408 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 3.8866. Min Range: -3.8866

Max Act: 3.6989. Min Act: -0.1700

Data Index: 1021832 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 3.8866. Min Range: -3.8866

Max Act: 3.7614. Min Act: -0.1700

Data Index: 331042 (C4 (Web Text))

Max Activating Token Index: 770

Text #16

Max Range: 3.8866. Min Range: -3.8866

Max Act: 3.6989. Min Act: -0.1700

Data Index: 214874 (C4 (Web Text))

Max Activating Token Index: 916

Text #17

Max Range: 3.8866. Min Range: -3.8866

Max Act: 3.6989. Min Act: -0.1700

Data Index: 1183514 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 3.8866. Min Range: -3.8866

Max Act: 3.6676. Min Act: -0.1700

Data Index: 931025 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 3.8866. Min Range: -3.8866

Max Act: 3.7301. Min Act: -0.1700

Data Index: 683637 (C4 (Web Text))

Max Activating Token Index: 943