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

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

Neuron 2031 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6989. Min Range: -3.6989

Max Act: 3.6833. Min Act: -0.1700

Data Index: 765415 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 3.6989. Min Range: -3.6989

Max Act: 3.6989. Min Act: -0.1700

Data Index: 1255403 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 3.6989. Min Range: -3.6989

Max Act: 3.6050. Min Act: -0.1700

Data Index: 1142221 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 3.6989. Min Range: -3.6989

Max Act: 3.5580. Min Act: -0.1700

Data Index: 311850 (C4 (Web Text))

Max Activating Token Index: 314

Text #4

Max Range: 3.6989. Min Range: -3.6989

Max Act: 3.5737. Min Act: -0.1700

Data Index: 926167 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 3.6989. Min Range: -3.6989

Max Act: 3.5580. Min Act: -0.1700

Data Index: 415481 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 3.6989. Min Range: -3.6989

Max Act: 3.4954. Min Act: -0.1700

Data Index: 692487 (C4 (Web Text))

Max Activating Token Index: 819

Text #7

Max Range: 3.6989. Min Range: -3.6989

Max Act: 3.5267. Min Act: -0.1700

Data Index: 1129145 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 3.6989. Min Range: -3.6989

Max Act: 3.5111. Min Act: -0.1700

Data Index: 711166 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 3.6989. Min Range: -3.6989

Max Act: 3.5580. Min Act: -0.1700

Data Index: 530542 (C4 (Web Text))

Max Activating Token Index: 884

Text #10

Max Range: 3.6989. Min Range: -3.6989

Max Act: 3.5111. Min Act: -0.1700

Data Index: 1188034 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 3.6989. Min Range: -3.6989

Max Act: 3.4954. Min Act: -0.1700

Data Index: 756968 (C4 (Web Text))

Max Activating Token Index: 592

Text #12

Max Range: 3.6989. Min Range: -3.6989

Max Act: 3.5424. Min Act: -0.1700

Data Index: 311433 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 3.6989. Min Range: -3.6989

Max Act: 3.5111. Min Act: -0.1700

Data Index: 395038 (C4 (Web Text))

Max Activating Token Index: 722

Text #14

Max Range: 3.6989. Min Range: -3.6989

Max Act: 3.4954. Min Act: -0.1700

Data Index: 68195 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 3.6989. Min Range: -3.6989

Max Act: 3.5111. Min Act: -0.1700

Data Index: 412942 (C4 (Web Text))

Max Activating Token Index: 732

Text #16

Max Range: 3.6989. Min Range: -3.6989

Max Act: 3.4954. Min Act: -0.1700

Data Index: 720576 (C4 (Web Text))

Max Activating Token Index: 313

Text #17

Max Range: 3.6989. Min Range: -3.6989

Max Act: 3.4954. Min Act: -0.1700

Data Index: 132849 (C4 (Web Text))

Max Activating Token Index: 622

Text #18

Max Range: 3.6989. Min Range: -3.6989

Max Act: 3.4327. Min Act: -0.1700

Data Index: 394452 (C4 (Web Text))

Max Activating Token Index: 530

Text #19

Max Range: 3.6989. Min Range: -3.6989

Max Act: 3.4954. Min Act: -0.1700

Data Index: 33468 (C4 (Web Text))

Max Activating Token Index: 250