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

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

Neuron 1087 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: 3.9799. Min Range: -3.9799

Max Act: 3.9799. Min Act: -0.1700

Data Index: 1269487 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 3.9799. Min Range: -3.9799

Max Act: 3.7766. Min Act: -0.1700

Data Index: 1268111 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 3.9799. Min Range: -3.9799

Max Act: 3.7609. Min Act: -0.1700

Data Index: 1002809 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 3.9799. Min Range: -3.9799

Max Act: 3.7609. Min Act: -0.1700

Data Index: 1129603 (C4 (Web Text))

Max Activating Token Index: 586

Text #4

Max Range: 3.9799. Min Range: -3.9799

Max Act: 3.8079. Min Act: -0.1700

Data Index: 271620 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 3.9799. Min Range: -3.9799

Max Act: 3.6671. Min Act: -0.1700

Data Index: 534216 (C4 (Web Text))

Max Activating Token Index: 418

Text #6

Max Range: 3.9799. Min Range: -3.9799

Max Act: 3.7297. Min Act: -0.1700

Data Index: 447832 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 3.9799. Min Range: -3.9799

Max Act: 3.6827. Min Act: -0.1700

Data Index: 286112 (C4 (Web Text))

Max Activating Token Index: 214

Text #8

Max Range: 3.9799. Min Range: -3.9799

Max Act: 3.6827. Min Act: -0.1700

Data Index: 651039 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 3.9799. Min Range: -3.9799

Max Act: 3.6671. Min Act: -0.1700

Data Index: 16886 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 3.9799. Min Range: -3.9799

Max Act: 3.6514. Min Act: -0.1700

Data Index: 107313 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 3.9799. Min Range: -3.9799

Max Act: 3.6827. Min Act: -0.1700

Data Index: 116270 (C4 (Web Text))

Max Activating Token Index: 958

Text #12

Max Range: 3.9799. Min Range: -3.9799

Max Act: 3.6514. Min Act: -0.1700

Data Index: 455161 (C4 (Web Text))

Max Activating Token Index: 355

Text #13

Max Range: 3.9799. Min Range: -3.9799

Max Act: 3.6358. Min Act: -0.1700

Data Index: 1338021 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 3.9799. Min Range: -3.9799

Max Act: 3.6514. Min Act: -0.1700

Data Index: 520088 (C4 (Web Text))

Max Activating Token Index: 803

Text #15

Max Range: 3.9799. Min Range: -3.9799

Max Act: 3.6514. Min Act: -0.1700

Data Index: 723457 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 3.9799. Min Range: -3.9799

Max Act: 3.6358. Min Act: -0.1700

Data Index: 1038670 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 3.9799. Min Range: -3.9799

Max Act: 3.6514. Min Act: -0.1700

Data Index: 631832 (C4 (Web Text))

Max Activating Token Index: 169

Text #18

Max Range: 3.9799. Min Range: -3.9799

Max Act: 3.6045. Min Act: -0.1700

Data Index: 221140 (C4 (Web Text))

Max Activating Token Index: 587

Text #19

Max Range: 3.9799. Min Range: -3.9799

Max Act: 3.6201. Min Act: -0.1700

Data Index: 231506 (C4 (Web Text))

Max Activating Token Index: 77