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

Dataset: Open Web Text

Neuron 4071 in Layer 27

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.8320. Min Range: -6.8320

Max Act: 6.8320. Min Act: -0.1700

Data Index: 561631 (Open Web Text)

Max Activating Token Index: 840

Text #1

Max Range: 6.8320. Min Range: -6.8320

Max Act: 6.6757. Min Act: -0.1700

Data Index: 470682 (Open Web Text)

Max Activating Token Index: 790

Text #2

Max Range: 6.8320. Min Range: -6.8320

Max Act: 6.5820. Min Act: -0.1700

Data Index: 3736894 (Open Web Text)

Max Activating Token Index: 968

Text #3

Max Range: 6.8320. Min Range: -6.8320

Max Act: 6.5507. Min Act: -0.1700

Data Index: 4398498 (Open Web Text)

Max Activating Token Index: 881

Text #4

Max Range: 6.8320. Min Range: -6.8320

Max Act: 6.4882. Min Act: -0.1700

Data Index: 7879118 (Open Web Text)

Max Activating Token Index: 400

Text #5

Max Range: 6.8320. Min Range: -6.8320

Max Act: 6.4257. Min Act: -0.1700

Data Index: 2415407 (Open Web Text)

Max Activating Token Index: 921

Text #6

Max Range: 6.8320. Min Range: -6.8320

Max Act: 6.3945. Min Act: -0.1700

Data Index: 74719 (Open Web Text)

Max Activating Token Index: 520

Text #7

Max Range: 6.8320. Min Range: -6.8320

Max Act: 6.3632. Min Act: -0.1700

Data Index: 754560 (Open Web Text)

Max Activating Token Index: 119

Text #8

Max Range: 6.8320. Min Range: -6.8320

Max Act: 6.3632. Min Act: -0.1700

Data Index: 7139258 (Open Web Text)

Max Activating Token Index: 878

Text #9

Max Range: 6.8320. Min Range: -6.8320

Max Act: 6.3632. Min Act: -0.1700

Data Index: 4608489 (Open Web Text)

Max Activating Token Index: 995

Text #10

Max Range: 6.8320. Min Range: -6.8320

Max Act: 6.3320. Min Act: -0.1700

Data Index: 1182626 (Open Web Text)

Max Activating Token Index: 804

Text #11

Max Range: 6.8320. Min Range: -6.8320

Max Act: 6.3320. Min Act: -0.1700

Data Index: 6214720 (Open Web Text)

Max Activating Token Index: 684

Text #12

Max Range: 6.8320. Min Range: -6.8320

Max Act: 6.3007. Min Act: -0.1700

Data Index: 2486656 (Open Web Text)

Max Activating Token Index: 387

Text #13

Max Range: 6.8320. Min Range: -6.8320

Max Act: 6.2695. Min Act: -0.1700

Data Index: 6899231 (Open Web Text)

Max Activating Token Index: 289

Text #14

Max Range: 6.8320. Min Range: -6.8320

Max Act: 6.2695. Min Act: -0.1700

Data Index: 6367023 (Open Web Text)

Max Activating Token Index: 810

Text #15

Max Range: 6.8320. Min Range: -6.8320

Max Act: 6.3007. Min Act: -0.1700

Data Index: 8023613 (Open Web Text)

Max Activating Token Index: 225

Text #16

Max Range: 6.8320. Min Range: -6.8320

Max Act: 6.2695. Min Act: -0.1700

Data Index: 722981 (Open Web Text)

Max Activating Token Index: 246

Text #17

Max Range: 6.8320. Min Range: -6.8320

Max Act: 6.2382. Min Act: -0.1700

Data Index: 4065512 (Open Web Text)

Max Activating Token Index: 153

Text #18

Max Range: 6.8320. Min Range: -6.8320

Max Act: 6.2382. Min Act: -0.1700

Data Index: 4208752 (Open Web Text)

Max Activating Token Index: 958

Text #19

Max Range: 6.8320. Min Range: -6.8320

Max Act: 6.2382. Min Act: -0.1700

Data Index: 791133 (Open Web Text)

Max Activating Token Index: 302