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

Dataset: Open Web Text

Neuron 2787 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: 4.1593. Min Range: -4.1593

Max Act: 4.1593. Min Act: -0.1700

Data Index: 6390124 (Open Web Text)

Max Activating Token Index: 240

Text #1

Max Range: 4.1593. Min Range: -4.1593

Max Act: 4.1148. Min Act: -0.1700

Data Index: 4633781 (Open Web Text)

Max Activating Token Index: 616

Text #2

Max Range: 4.1593. Min Range: -4.1593

Max Act: 4.0790. Min Act: -0.1700

Data Index: 1910378 (Open Web Text)

Max Activating Token Index: 473

Text #3

Max Range: 4.1593. Min Range: -4.1593

Max Act: 4.0336. Min Act: -0.1700

Data Index: 3640113 (Open Web Text)

Max Activating Token Index: 203

Text #4

Max Range: 4.1593. Min Range: -4.1593

Max Act: 4.0890. Min Act: -0.1700

Data Index: 1154606 (Open Web Text)

Max Activating Token Index: 898

Text #5

Max Range: 4.1593. Min Range: -4.1593

Max Act: 4.0428. Min Act: -0.1700

Data Index: 4794736 (Open Web Text)

Max Activating Token Index: 636

Text #6

Max Range: 4.1593. Min Range: -4.1593

Max Act: 4.0469. Min Act: -0.1700

Data Index: 4813954 (Open Web Text)

Max Activating Token Index: 368

Text #7

Max Range: 4.1593. Min Range: -4.1593

Max Act: 4.0380. Min Act: -0.1700

Data Index: 8676929 (Open Web Text)

Max Activating Token Index: 532

Text #8

Max Range: 4.1593. Min Range: -4.1593

Max Act: 4.0143. Min Act: -0.1700

Data Index: 4997027 (Open Web Text)

Max Activating Token Index: 970

Text #9

Max Range: 4.1593. Min Range: -4.1593

Max Act: 4.0173. Min Act: -0.1700

Data Index: 2685583 (Open Web Text)

Max Activating Token Index: 772

Text #10

Max Range: 4.1593. Min Range: -4.1593

Max Act: 3.9904. Min Act: -0.1700

Data Index: 2134141 (Open Web Text)

Max Activating Token Index: 383

Text #11

Max Range: 4.1593. Min Range: -4.1593

Max Act: 4.0159. Min Act: -0.1700

Data Index: 4931792 (Open Web Text)

Max Activating Token Index: 121

Text #12

Max Range: 4.1593. Min Range: -4.1593

Max Act: 4.0383. Min Act: -0.1700

Data Index: 5044014 (Open Web Text)

Max Activating Token Index: 782

Text #13

Max Range: 4.1593. Min Range: -4.1593

Max Act: 3.9328. Min Act: -0.1700

Data Index: 8433032 (Open Web Text)

Max Activating Token Index: 764

Text #14

Max Range: 4.1593. Min Range: -4.1593

Max Act: 3.9533. Min Act: -0.1700

Data Index: 5708944 (Open Web Text)

Max Activating Token Index: 373

Text #15

Max Range: 4.1593. Min Range: -4.1593

Max Act: 3.9642. Min Act: -0.1700

Data Index: 8228868 (Open Web Text)

Max Activating Token Index: 990

Text #16

Max Range: 4.1593. Min Range: -4.1593

Max Act: 3.9247. Min Act: -0.1700

Data Index: 4325679 (Open Web Text)

Max Activating Token Index: 878

Text #17

Max Range: 4.1593. Min Range: -4.1593

Max Act: 3.9063. Min Act: -0.1700

Data Index: 5334021 (Open Web Text)

Max Activating Token Index: 451

Text #18

Max Range: 4.1593. Min Range: -4.1593

Max Act: 3.9300. Min Act: -0.1700

Data Index: 3448496 (Open Web Text)

Max Activating Token Index: 705

Text #19

Max Range: 4.1593. Min Range: -4.1593

Max Act: 3.9672. Min Act: -0.1700

Data Index: 3006922 (Open Web Text)

Max Activating Token Index: 927