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

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

Neuron 1838 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: 4.0309. Min Range: -4.0309

Max Act: 3.9996. Min Act: -0.1700

Data Index: 20001 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 4.0309. Min Range: -4.0309

Max Act: 4.0309. Min Act: -0.1700

Data Index: 1092291 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 4.0309. Min Range: -4.0309

Max Act: 3.8432. Min Act: -0.1700

Data Index: 295220 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 4.0309. Min Range: -4.0309

Max Act: 3.8745. Min Act: -0.1700

Data Index: 388023 (C4 (Web Text))

Max Activating Token Index: 613

Text #4

Max Range: 4.0309. Min Range: -4.0309

Max Act: 3.8432. Min Act: -0.1700

Data Index: 1141991 (C4 (Web Text))

Max Activating Token Index: 926

Text #5

Max Range: 4.0309. Min Range: -4.0309

Max Act: 3.8432. Min Act: -0.1700

Data Index: 263491 (C4 (Web Text))

Max Activating Token Index: 518

Text #6

Max Range: 4.0309. Min Range: -4.0309

Max Act: 3.8120. Min Act: -0.1700

Data Index: 64986 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 4.0309. Min Range: -4.0309

Max Act: 3.7807. Min Act: -0.1700

Data Index: 462843 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 4.0309. Min Range: -4.0309

Max Act: 3.7807. Min Act: -0.1700

Data Index: 67670 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 4.0309. Min Range: -4.0309

Max Act: 3.7181. Min Act: -0.1700

Data Index: 502771 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 4.0309. Min Range: -4.0309

Max Act: 3.7181. Min Act: -0.1700

Data Index: 9897 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 4.0309. Min Range: -4.0309

Max Act: 3.6242. Min Act: -0.1700

Data Index: 1295168 (C4 (Web Text))

Max Activating Token Index: 604

Text #12

Max Range: 4.0309. Min Range: -4.0309

Max Act: 3.7181. Min Act: -0.1700

Data Index: 762506 (C4 (Web Text))

Max Activating Token Index: 226

Text #13

Max Range: 4.0309. Min Range: -4.0309

Max Act: 3.7807. Min Act: -0.1700

Data Index: 770657 (C4 (Web Text))

Max Activating Token Index: 194

Text #14

Max Range: 4.0309. Min Range: -4.0309

Max Act: 3.7181. Min Act: -0.1700

Data Index: 944191 (C4 (Web Text))

Max Activating Token Index: 1009

Text #15

Max Range: 4.0309. Min Range: -4.0309

Max Act: 3.7807. Min Act: -0.1700

Data Index: 116503 (C4 (Web Text))

Max Activating Token Index: 731

Text #16

Max Range: 4.0309. Min Range: -4.0309

Max Act: 3.6868. Min Act: -0.1700

Data Index: 906128 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 4.0309. Min Range: -4.0309

Max Act: 3.7181. Min Act: -0.1700

Data Index: 828354 (C4 (Web Text))

Max Activating Token Index: 915

Text #18

Max Range: 4.0309. Min Range: -4.0309

Max Act: 3.7181. Min Act: -0.1700

Data Index: 44091 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 4.0309. Min Range: -4.0309

Max Act: 3.7181. Min Act: -0.1700

Data Index: 236257 (C4 (Web Text))

Max Activating Token Index: 221