Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 48 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.3021. Min Range: -3.3021

Max Act: 3.3021. Min Act: -0.1700

Data Index: 650504 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 3.3021. Min Range: -3.3021

Max Act: 3.2706. Min Act: -0.1700

Data Index: 839382 (C4 (Web Text))

Max Activating Token Index: 708

Text #2

Max Range: 3.3021. Min Range: -3.3021

Max Act: 3.2706. Min Act: -0.1700

Data Index: 1353484 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 3.3021. Min Range: -3.3021

Max Act: 3.2549. Min Act: -0.1700

Data Index: 401300 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 3.3021. Min Range: -3.3021

Max Act: 3.2549. Min Act: -0.1700

Data Index: 517324 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 3.3021. Min Range: -3.3021

Max Act: 3.2392. Min Act: -0.1700

Data Index: 1149721 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 3.3021. Min Range: -3.3021

Max Act: 3.1920. Min Act: -0.1700

Data Index: 1213727 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 3.3021. Min Range: -3.3021

Max Act: 3.1920. Min Act: -0.1700

Data Index: 950920 (C4 (Web Text))

Max Activating Token Index: 908

Text #8

Max Range: 3.3021. Min Range: -3.3021

Max Act: 3.1920. Min Act: -0.1700

Data Index: 808791 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 3.3021. Min Range: -3.3021

Max Act: 3.1605. Min Act: -0.1700

Data Index: 661988 (C4 (Web Text))

Max Activating Token Index: 418

Text #10

Max Range: 3.3021. Min Range: -3.3021

Max Act: 3.1290. Min Act: -0.1700

Data Index: 91257 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 3.3021. Min Range: -3.3021

Max Act: 3.1605. Min Act: -0.1700

Data Index: 1142648 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 3.3021. Min Range: -3.3021

Max Act: 3.1605. Min Act: -0.1700

Data Index: 686793 (C4 (Web Text))

Max Activating Token Index: 28

Text #13

Max Range: 3.3021. Min Range: -3.3021

Max Act: 3.1290. Min Act: -0.1700

Data Index: 727843 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 3.3021. Min Range: -3.3021

Max Act: 3.1448. Min Act: -0.1700

Data Index: 976133 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 3.3021. Min Range: -3.3021

Max Act: 3.1290. Min Act: -0.1700

Data Index: 363202 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 3.3021. Min Range: -3.3021

Max Act: 3.1133. Min Act: -0.1700

Data Index: 1055205 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 3.3021. Min Range: -3.3021

Max Act: 3.0975. Min Act: -0.1700

Data Index: 937913 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 3.3021. Min Range: -3.3021

Max Act: 3.1290. Min Act: -0.1700

Data Index: 1324040 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 3.3021. Min Range: -3.3021

Max Act: 3.1290. Min Act: -0.1700

Data Index: 210173 (C4 (Web Text))

Max Activating Token Index: 267