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

Dataset: Open Web Text

Neuron 2984 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: 6.2942. Min Range: -6.2942

Max Act: 6.2942. Min Act: -0.1700

Data Index: 5078438 (Open Web Text)

Max Activating Token Index: 55

Text #1

Max Range: 6.2942. Min Range: -6.2942

Max Act: 6.2465. Min Act: -0.1700

Data Index: 2546427 (Open Web Text)

Max Activating Token Index: 315

Text #2

Max Range: 6.2942. Min Range: -6.2942

Max Act: 6.1422. Min Act: -0.1700

Data Index: 609774 (Open Web Text)

Max Activating Token Index: 854

Text #3

Max Range: 6.2942. Min Range: -6.2942

Max Act: 6.1403. Min Act: -0.1700

Data Index: 3776215 (Open Web Text)

Max Activating Token Index: 706

Text #4

Max Range: 6.2942. Min Range: -6.2942

Max Act: 6.1100. Min Act: -0.1700

Data Index: 8747281 (Open Web Text)

Max Activating Token Index: 223

Text #5

Max Range: 6.2942. Min Range: -6.2942

Max Act: 6.1074. Min Act: -0.1700

Data Index: 8825606 (Open Web Text)

Max Activating Token Index: 996

Text #6

Max Range: 6.2942. Min Range: -6.2942

Max Act: 6.0592. Min Act: -0.1700

Data Index: 4923743 (Open Web Text)

Max Activating Token Index: 630

Text #7

Max Range: 6.2942. Min Range: -6.2942

Max Act: 6.1113. Min Act: -0.1700

Data Index: 5228686 (Open Web Text)

Max Activating Token Index: 421

Text #8

Max Range: 6.2942. Min Range: -6.2942

Max Act: 5.9932. Min Act: -0.1700

Data Index: 689355 (Open Web Text)

Max Activating Token Index: 964

Text #9

Max Range: 6.2942. Min Range: -6.2942

Max Act: 5.9948. Min Act: -0.1700

Data Index: 6724471 (Open Web Text)

Max Activating Token Index: 777

Text #10

Max Range: 6.2942. Min Range: -6.2942

Max Act: 5.9511. Min Act: -0.1700

Data Index: 6074648 (Open Web Text)

Max Activating Token Index: 700

Text #11

Max Range: 6.2942. Min Range: -6.2942

Max Act: 5.9641. Min Act: -0.1700

Data Index: 7095171 (Open Web Text)

Max Activating Token Index: 888

Text #12

Max Range: 6.2942. Min Range: -6.2942

Max Act: 5.9949. Min Act: -0.1700

Data Index: 3315908 (Open Web Text)

Max Activating Token Index: 461

Text #13

Max Range: 6.2942. Min Range: -6.2942

Max Act: 5.9722. Min Act: -0.1700

Data Index: 5567702 (Open Web Text)

Max Activating Token Index: 54

Text #14

Max Range: 6.2942. Min Range: -6.2942

Max Act: 5.9576. Min Act: -0.1700

Data Index: 5091156 (Open Web Text)

Max Activating Token Index: 525

Text #15

Max Range: 6.2942. Min Range: -6.2942

Max Act: 5.9679. Min Act: -0.1700

Data Index: 1342936 (Open Web Text)

Max Activating Token Index: 43

Text #16

Max Range: 6.2942. Min Range: -6.2942

Max Act: 6.0092. Min Act: -0.1700

Data Index: 825525 (Open Web Text)

Max Activating Token Index: 986

Text #17

Max Range: 6.2942. Min Range: -6.2942

Max Act: 5.9272. Min Act: -0.1700

Data Index: 3025712 (Open Web Text)

Max Activating Token Index: 556

Text #18

Max Range: 6.2942. Min Range: -6.2942

Max Act: 5.9728. Min Act: -0.1700

Data Index: 3359374 (Open Web Text)

Max Activating Token Index: 598

Text #19

Max Range: 6.2942. Min Range: -6.2942

Max Act: 5.9760. Min Act: -0.1700

Data Index: 2114945 (Open Web Text)

Max Activating Token Index: 627