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

Dataset: Open Web Text

Neuron 559 in Layer 20

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.6379. Min Range: -7.6379

Max Act: 7.6379. Min Act: -0.1700

Data Index: 8738328 (Open Web Text)

Max Activating Token Index: 906

Text #1

Max Range: 7.6379. Min Range: -7.6379

Max Act: 7.4816. Min Act: -0.1700

Data Index: 6227437 (Open Web Text)

Max Activating Token Index: 828

Text #2

Max Range: 7.6379. Min Range: -7.6379

Max Act: 7.3879. Min Act: -0.1700

Data Index: 5150815 (Open Web Text)

Max Activating Token Index: 236

Text #3

Max Range: 7.6379. Min Range: -7.6379

Max Act: 7.3879. Min Act: -0.1700

Data Index: 5163622 (Open Web Text)

Max Activating Token Index: 474

Text #4

Max Range: 7.6379. Min Range: -7.6379

Max Act: 7.3566. Min Act: -0.1700

Data Index: 2818076 (Open Web Text)

Max Activating Token Index: 722

Text #5

Max Range: 7.6379. Min Range: -7.6379

Max Act: 7.3566. Min Act: -0.1700

Data Index: 6965320 (Open Web Text)

Max Activating Token Index: 241

Text #6

Max Range: 7.6379. Min Range: -7.6379

Max Act: 7.2941. Min Act: -0.1700

Data Index: 5861350 (Open Web Text)

Max Activating Token Index: 274

Text #7

Max Range: 7.6379. Min Range: -7.6379

Max Act: 7.2004. Min Act: -0.1700

Data Index: 5028189 (Open Web Text)

Max Activating Token Index: 651

Text #8

Max Range: 7.6379. Min Range: -7.6379

Max Act: 7.2004. Min Act: -0.1700

Data Index: 1905398 (Open Web Text)

Max Activating Token Index: 126

Text #9

Max Range: 7.6379. Min Range: -7.6379

Max Act: 7.2004. Min Act: -0.1700

Data Index: 1453036 (Open Web Text)

Max Activating Token Index: 995

Text #10

Max Range: 7.6379. Min Range: -7.6379

Max Act: 7.2004. Min Act: -0.1700

Data Index: 7434207 (Open Web Text)

Max Activating Token Index: 496

Text #11

Max Range: 7.6379. Min Range: -7.6379

Max Act: 7.1691. Min Act: -0.1700

Data Index: 2340577 (Open Web Text)

Max Activating Token Index: 724

Text #12

Max Range: 7.6379. Min Range: -7.6379

Max Act: 7.1379. Min Act: -0.1700

Data Index: 8738334 (Open Web Text)

Max Activating Token Index: 324

Text #13

Max Range: 7.6379. Min Range: -7.6379

Max Act: 7.1379. Min Act: -0.1700

Data Index: 8523264 (Open Web Text)

Max Activating Token Index: 637

Text #14

Max Range: 7.6379. Min Range: -7.6379

Max Act: 7.1379. Min Act: -0.1700

Data Index: 122742 (Open Web Text)

Max Activating Token Index: 693

Text #15

Max Range: 7.6379. Min Range: -7.6379

Max Act: 7.1379. Min Act: -0.1700

Data Index: 6834206 (Open Web Text)

Max Activating Token Index: 382

Text #16

Max Range: 7.6379. Min Range: -7.6379

Max Act: 7.0754. Min Act: -0.1700

Data Index: 4775121 (Open Web Text)

Max Activating Token Index: 231

Text #17

Max Range: 7.6379. Min Range: -7.6379

Max Act: 7.1066. Min Act: -0.1700

Data Index: 3648537 (Open Web Text)

Max Activating Token Index: 176

Text #18

Max Range: 7.6379. Min Range: -7.6379

Max Act: 7.1066. Min Act: -0.1700

Data Index: 4396960 (Open Web Text)

Max Activating Token Index: 956

Text #19

Max Range: 7.6379. Min Range: -7.6379

Max Act: 7.0754. Min Act: -0.1700

Data Index: 2732019 (Open Web Text)

Max Activating Token Index: 730