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

Dataset: Open Web Text

Neuron 3846 in Layer 39

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.6771. Min Range: -8.6771

Max Act: 8.6771. Min Act: -0.1700

Data Index: 6391675 (Open Web Text)

Max Activating Token Index: 975

Text #1

Max Range: 8.6771. Min Range: -8.6771

Max Act: 7.6459. Min Act: -0.1700

Data Index: 2069153 (Open Web Text)

Max Activating Token Index: 758

Text #2

Max Range: 8.6771. Min Range: -8.6771

Max Act: 7.5834. Min Act: -0.1700

Data Index: 5675067 (Open Web Text)

Max Activating Token Index: 735

Text #3

Max Range: 8.6771. Min Range: -8.6771

Max Act: 7.5209. Min Act: -0.1700

Data Index: 6186713 (Open Web Text)

Max Activating Token Index: 627

Text #4

Max Range: 8.6771. Min Range: -8.6771

Max Act: 7.4896. Min Act: -0.1700

Data Index: 6172292 (Open Web Text)

Max Activating Token Index: 801

Text #5

Max Range: 8.6771. Min Range: -8.6771

Max Act: 7.4271. Min Act: -0.1700

Data Index: 3667353 (Open Web Text)

Max Activating Token Index: 654

Text #6

Max Range: 8.6771. Min Range: -8.6771

Max Act: 7.4271. Min Act: -0.1700

Data Index: 3446533 (Open Web Text)

Max Activating Token Index: 393

Text #7

Max Range: 8.6771. Min Range: -8.6771

Max Act: 7.3646. Min Act: -0.1700

Data Index: 3408253 (Open Web Text)

Max Activating Token Index: 303

Text #8

Max Range: 8.6771. Min Range: -8.6771

Max Act: 7.3334. Min Act: -0.1700

Data Index: 863022 (Open Web Text)

Max Activating Token Index: 278

Text #9

Max Range: 8.6771. Min Range: -8.6771

Max Act: 7.3334. Min Act: -0.1700

Data Index: 684138 (Open Web Text)

Max Activating Token Index: 111

Text #10

Max Range: 8.6771. Min Range: -8.6771

Max Act: 7.3334. Min Act: -0.1700

Data Index: 7972735 (Open Web Text)

Max Activating Token Index: 107

Text #11

Max Range: 8.6771. Min Range: -8.6771

Max Act: 7.3021. Min Act: -0.1700

Data Index: 1482960 (Open Web Text)

Max Activating Token Index: 293

Text #12

Max Range: 8.6771. Min Range: -8.6771

Max Act: 7.3021. Min Act: -0.1700

Data Index: 3022342 (Open Web Text)

Max Activating Token Index: 480

Text #13

Max Range: 8.6771. Min Range: -8.6771

Max Act: 7.3021. Min Act: -0.1700

Data Index: 7790284 (Open Web Text)

Max Activating Token Index: 549

Text #14

Max Range: 8.6771. Min Range: -8.6771

Max Act: 7.3021. Min Act: -0.1700

Data Index: 2711710 (Open Web Text)

Max Activating Token Index: 839

Text #15

Max Range: 8.6771. Min Range: -8.6771

Max Act: 7.2709. Min Act: -0.1700

Data Index: 781043 (Open Web Text)

Max Activating Token Index: 839

Text #16

Max Range: 8.6771. Min Range: -8.6771

Max Act: 7.2709. Min Act: -0.1700

Data Index: 5274520 (Open Web Text)

Max Activating Token Index: 749

Text #17

Max Range: 8.6771. Min Range: -8.6771

Max Act: 7.2396. Min Act: -0.1700

Data Index: 2209100 (Open Web Text)

Max Activating Token Index: 599

Text #18

Max Range: 8.6771. Min Range: -8.6771

Max Act: 7.1771. Min Act: -0.1700

Data Index: 4683213 (Open Web Text)

Max Activating Token Index: 669

Text #19

Max Range: 8.6771. Min Range: -8.6771

Max Act: 7.2084. Min Act: -0.1700

Data Index: 1038939 (Open Web Text)

Max Activating Token Index: 184