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

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

Neuron 1301 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5083. Min Range: -5.5083

Max Act: 5.5083. Min Act: -0.1700

Data Index: 805059 (C4 (Web Text))

Max Activating Token Index: 813

Text #1

Max Range: 5.5083. Min Range: -5.5083

Max Act: 5.3520. Min Act: -0.1700

Data Index: 295534 (C4 (Web Text))

Max Activating Token Index: 769

Text #2

Max Range: 5.5083. Min Range: -5.5083

Max Act: 5.3208. Min Act: -0.1700

Data Index: 1000307 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 5.5083. Min Range: -5.5083

Max Act: 5.3208. Min Act: -0.1700

Data Index: 44768 (C4 (Web Text))

Max Activating Token Index: 1015

Text #4

Max Range: 5.5083. Min Range: -5.5083

Max Act: 5.2270. Min Act: -0.1700

Data Index: 318884 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 5.5083. Min Range: -5.5083

Max Act: 5.2583. Min Act: -0.1700

Data Index: 138820 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 5.5083. Min Range: -5.5083

Max Act: 5.1958. Min Act: -0.1700

Data Index: 1117647 (C4 (Web Text))

Max Activating Token Index: 598

Text #7

Max Range: 5.5083. Min Range: -5.5083

Max Act: 5.1645. Min Act: -0.1700

Data Index: 447706 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 5.5083. Min Range: -5.5083

Max Act: 5.1958. Min Act: -0.1700

Data Index: 801561 (C4 (Web Text))

Max Activating Token Index: 949

Text #9

Max Range: 5.5083. Min Range: -5.5083

Max Act: 5.1333. Min Act: -0.1700

Data Index: 659274 (C4 (Web Text))

Max Activating Token Index: 227

Text #10

Max Range: 5.5083. Min Range: -5.5083

Max Act: 5.1645. Min Act: -0.1700

Data Index: 679337 (C4 (Web Text))

Max Activating Token Index: 979

Text #11

Max Range: 5.5083. Min Range: -5.5083

Max Act: 5.0708. Min Act: -0.1700

Data Index: 528195 (C4 (Web Text))

Max Activating Token Index: 916

Text #12

Max Range: 5.5083. Min Range: -5.5083

Max Act: 5.0708. Min Act: -0.1700

Data Index: 611684 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 5.5083. Min Range: -5.5083

Max Act: 5.1020. Min Act: -0.1700

Data Index: 1275429 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 5.5083. Min Range: -5.5083

Max Act: 5.1020. Min Act: -0.1700

Data Index: 1311269 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 5.5083. Min Range: -5.5083

Max Act: 5.1020. Min Act: -0.1700

Data Index: 879321 (C4 (Web Text))

Max Activating Token Index: 431

Text #16

Max Range: 5.5083. Min Range: -5.5083

Max Act: 5.0708. Min Act: -0.1700

Data Index: 94350 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 5.5083. Min Range: -5.5083

Max Act: 5.0395. Min Act: -0.1700

Data Index: 824591 (C4 (Web Text))

Max Activating Token Index: 999

Text #18

Max Range: 5.5083. Min Range: -5.5083

Max Act: 5.0708. Min Act: -0.1700

Data Index: 174760 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 5.5083. Min Range: -5.5083

Max Act: 5.0395. Min Act: -0.1700

Data Index: 65712 (C4 (Web Text))

Max Activating Token Index: 924