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

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

Neuron 250 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5203. Min Range: -3.5203

Max Act: 3.5203. Min Act: -0.1700

Data Index: 1237882 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 3.5203. Min Range: -3.5203

Max Act: 3.4890. Min Act: -0.1700

Data Index: 1357367 (C4 (Web Text))

Max Activating Token Index: 360

Text #2

Max Range: 3.5203. Min Range: -3.5203

Max Act: 3.2065. Min Act: -0.1700

Data Index: 1293345 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 3.5203. Min Range: -3.5203

Max Act: 3.3322. Min Act: -0.1700

Data Index: 421746 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 3.5203. Min Range: -3.5203

Max Act: 3.0804. Min Act: -0.1700

Data Index: 615573 (C4 (Web Text))

Max Activating Token Index: 628

Text #5

Max Range: 3.5203. Min Range: -3.5203

Max Act: 3.1277. Min Act: -0.1700

Data Index: 127644 (C4 (Web Text))

Max Activating Token Index: 504

Text #6

Max Range: 3.5203. Min Range: -3.5203

Max Act: 3.0489. Min Act: -0.1700

Data Index: 311044 (C4 (Web Text))

Max Activating Token Index: 909

Text #7

Max Range: 3.5203. Min Range: -3.5203

Max Act: 3.0647. Min Act: -0.1700

Data Index: 671601 (C4 (Web Text))

Max Activating Token Index: 717

Text #8

Max Range: 3.5203. Min Range: -3.5203

Max Act: 3.0804. Min Act: -0.1700

Data Index: 796797 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 3.5203. Min Range: -3.5203

Max Act: 3.0173. Min Act: -0.1700

Data Index: 1293807 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 3.5203. Min Range: -3.5203

Max Act: 3.0331. Min Act: -0.1700

Data Index: 120006 (C4 (Web Text))

Max Activating Token Index: 863

Text #11

Max Range: 3.5203. Min Range: -3.5203

Max Act: 3.0331. Min Act: -0.1700

Data Index: 179545 (C4 (Web Text))

Max Activating Token Index: 683

Text #12

Max Range: 3.5203. Min Range: -3.5203

Max Act: 3.0015. Min Act: -0.1700

Data Index: 479051 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 3.5203. Min Range: -3.5203

Max Act: 3.0962. Min Act: -0.1700

Data Index: 7623 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 3.5203. Min Range: -3.5203

Max Act: 2.9540. Min Act: -0.1700

Data Index: 1003363 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 3.5203. Min Range: -3.5203

Max Act: 3.0015. Min Act: -0.1700

Data Index: 712947 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 3.5203. Min Range: -3.5203

Max Act: 3.0173. Min Act: -0.1700

Data Index: 56971 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 3.5203. Min Range: -3.5203

Max Act: 3.0015. Min Act: -0.1700

Data Index: 466387 (C4 (Web Text))

Max Activating Token Index: 514

Text #18

Max Range: 3.5203. Min Range: -3.5203

Max Act: 2.9699. Min Act: -0.1700

Data Index: 1054814 (C4 (Web Text))

Max Activating Token Index: 454

Text #19

Max Range: 3.5203. Min Range: -3.5203

Max Act: 2.9382. Min Act: -0.1700

Data Index: 132871 (C4 (Web Text))

Max Activating Token Index: 802