Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 3599 in Layer 40

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')

Text #0

Max Range: 9.1016. Min Range: -9.1016

Max Act: 9.1016. Min Act: -0.1700

Data Index: 818315 (Open Web Text)

Max Activating Token Index: 333

Text #1

Max Range: 9.1016. Min Range: -9.1016

Max Act: 8.9141. Min Act: -0.1700

Data Index: 7721793 (Open Web Text)

Max Activating Token Index: 397

Text #2

Max Range: 9.1016. Min Range: -9.1016

Max Act: 8.7266. Min Act: -0.1700

Data Index: 1261643 (Open Web Text)

Max Activating Token Index: 900

Text #3

Max Range: 9.1016. Min Range: -9.1016

Max Act: 8.6016. Min Act: -0.1700

Data Index: 6319460 (Open Web Text)

Max Activating Token Index: 485

Text #4

Max Range: 9.1016. Min Range: -9.1016

Max Act: 8.5391. Min Act: -0.1700

Data Index: 6313743 (Open Web Text)

Max Activating Token Index: 713

Text #5

Max Range: 9.1016. Min Range: -9.1016

Max Act: 8.5391. Min Act: -0.1700

Data Index: 998221 (Open Web Text)

Max Activating Token Index: 438

Text #6

Max Range: 9.1016. Min Range: -9.1016

Max Act: 8.4141. Min Act: -0.1700

Data Index: 3548277 (Open Web Text)

Max Activating Token Index: 278

Text #7

Max Range: 9.1016. Min Range: -9.1016

Max Act: 8.4141. Min Act: -0.1700

Data Index: 812795 (Open Web Text)

Max Activating Token Index: 866

Text #8

Max Range: 9.1016. Min Range: -9.1016

Max Act: 8.4141. Min Act: -0.1700

Data Index: 499739 (Open Web Text)

Max Activating Token Index: 363

Text #9

Max Range: 9.1016. Min Range: -9.1016

Max Act: 8.4141. Min Act: -0.1700

Data Index: 7450123 (Open Web Text)

Max Activating Token Index: 729

Text #10

Max Range: 9.1016. Min Range: -9.1016

Max Act: 8.3516. Min Act: -0.1700

Data Index: 7697909 (Open Web Text)

Max Activating Token Index: 144

Text #11

Max Range: 9.1016. Min Range: -9.1016

Max Act: 8.2891. Min Act: -0.1700

Data Index: 5065958 (Open Web Text)

Max Activating Token Index: 975

Text #12

Max Range: 9.1016. Min Range: -9.1016

Max Act: 8.2891. Min Act: -0.1700

Data Index: 3989972 (Open Web Text)

Max Activating Token Index: 353

Text #13

Max Range: 9.1016. Min Range: -9.1016

Max Act: 8.2891. Min Act: -0.1700

Data Index: 3023332 (Open Web Text)

Max Activating Token Index: 418

Text #14

Max Range: 9.1016. Min Range: -9.1016

Max Act: 8.2266. Min Act: -0.1700

Data Index: 713003 (Open Web Text)

Max Activating Token Index: 766

Text #15

Max Range: 9.1016. Min Range: -9.1016

Max Act: 8.2891. Min Act: -0.1700

Data Index: 4677659 (Open Web Text)

Max Activating Token Index: 536

Text #16

Max Range: 9.1016. Min Range: -9.1016

Max Act: 8.2266. Min Act: -0.1700

Data Index: 4873679 (Open Web Text)

Max Activating Token Index: 322

Text #17

Max Range: 9.1016. Min Range: -9.1016

Max Act: 8.2266. Min Act: -0.1700

Data Index: 3245051 (Open Web Text)

Max Activating Token Index: 969

Text #18

Max Range: 9.1016. Min Range: -9.1016

Max Act: 8.2266. Min Act: -0.1700

Data Index: 7397140 (Open Web Text)

Max Activating Token Index: 907

Text #19

Max Range: 9.1016. Min Range: -9.1016

Max Act: 8.1641. Min Act: -0.1700

Data Index: 4328344 (Open Web Text)

Max Activating Token Index: 180