Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 57 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.6216. Min Range: -3.6216

Max Act: 3.6216. Min Act: -0.1700

Data Index: 2086437 (Open Web Text)

Max Activating Token Index: 556

Text #1

Max Range: 3.6216. Min Range: -3.6216

Max Act: 3.6099. Min Act: -0.1700

Data Index: 2238816 (Open Web Text)

Max Activating Token Index: 859

Text #2

Max Range: 3.6216. Min Range: -3.6216

Max Act: 3.5629. Min Act: -0.1700

Data Index: 7701931 (Open Web Text)

Max Activating Token Index: 850

Text #3

Max Range: 3.6216. Min Range: -3.6216

Max Act: 3.5557. Min Act: -0.1700

Data Index: 4520771 (Open Web Text)

Max Activating Token Index: 842

Text #4

Max Range: 3.6216. Min Range: -3.6216

Max Act: 3.4969. Min Act: -0.1700

Data Index: 8560299 (Open Web Text)

Max Activating Token Index: 888

Text #5

Max Range: 3.6216. Min Range: -3.6216

Max Act: 3.5089. Min Act: -0.1700

Data Index: 2237662 (Open Web Text)

Max Activating Token Index: 955

Text #6

Max Range: 3.6216. Min Range: -3.6216

Max Act: 3.4850. Min Act: -0.1700

Data Index: 5108279 (Open Web Text)

Max Activating Token Index: 350

Text #7

Max Range: 3.6216. Min Range: -3.6216

Max Act: 3.4643. Min Act: -0.1700

Data Index: 3338843 (Open Web Text)

Max Activating Token Index: 119

Text #8

Max Range: 3.6216. Min Range: -3.6216

Max Act: 3.4385. Min Act: -0.1700

Data Index: 3406001 (Open Web Text)

Max Activating Token Index: 983

Text #9

Max Range: 3.6216. Min Range: -3.6216

Max Act: 3.4401. Min Act: -0.1700

Data Index: 2420215 (Open Web Text)

Max Activating Token Index: 692

Text #10

Max Range: 3.6216. Min Range: -3.6216

Max Act: 3.4572. Min Act: -0.1700

Data Index: 7549942 (Open Web Text)

Max Activating Token Index: 164

Text #11

Max Range: 3.6216. Min Range: -3.6216

Max Act: 3.4112. Min Act: -0.1700

Data Index: 1081589 (Open Web Text)

Max Activating Token Index: 573

Text #12

Max Range: 3.6216. Min Range: -3.6216

Max Act: 3.4034. Min Act: -0.1700

Data Index: 3320425 (Open Web Text)

Max Activating Token Index: 961

Text #13

Max Range: 3.6216. Min Range: -3.6216

Max Act: 3.4011. Min Act: -0.1700

Data Index: 5248761 (Open Web Text)

Max Activating Token Index: 360

Text #14

Max Range: 3.6216. Min Range: -3.6216

Max Act: 3.3968. Min Act: -0.1700

Data Index: 3493518 (Open Web Text)

Max Activating Token Index: 757

Text #15

Max Range: 3.6216. Min Range: -3.6216

Max Act: 3.3883. Min Act: -0.1700

Data Index: 2765852 (Open Web Text)

Max Activating Token Index: 609

Text #16

Max Range: 3.6216. Min Range: -3.6216

Max Act: 3.3542. Min Act: -0.1700

Data Index: 5172330 (Open Web Text)

Max Activating Token Index: 450

Text #17

Max Range: 3.6216. Min Range: -3.6216

Max Act: 3.3494. Min Act: -0.1700

Data Index: 7358343 (Open Web Text)

Max Activating Token Index: 200

Text #18

Max Range: 3.6216. Min Range: -3.6216

Max Act: 3.3719. Min Act: -0.1700

Data Index: 7378044 (Open Web Text)

Max Activating Token Index: 908

Text #19

Max Range: 3.6216. Min Range: -3.6216

Max Act: 3.3652. Min Act: -0.1700

Data Index: 1959473 (Open Web Text)

Max Activating Token Index: 193