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

Dataset: Open Web Text

Neuron 587 in Layer 5

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: 2.3231. Min Range: -2.3231

Max Act: 2.3231. Min Act: -0.1700

Data Index: 844694 (Open Web Text)

Max Activating Token Index: 68

Text #1

Max Range: 2.3231. Min Range: -2.3231

Max Act: 2.2416. Min Act: -0.1700

Data Index: 3985034 (Open Web Text)

Max Activating Token Index: 216

Text #2

Max Range: 2.3231. Min Range: -2.3231

Max Act: 2.1900. Min Act: -0.1700

Data Index: 3800479 (Open Web Text)

Max Activating Token Index: 458

Text #3

Max Range: 2.3231. Min Range: -2.3231

Max Act: 2.1756. Min Act: -0.1700

Data Index: 1950875 (Open Web Text)

Max Activating Token Index: 483

Text #4

Max Range: 2.3231. Min Range: -2.3231

Max Act: 2.1476. Min Act: -0.1700

Data Index: 5442072 (Open Web Text)

Max Activating Token Index: 1003

Text #5

Max Range: 2.3231. Min Range: -2.3231

Max Act: 2.1444. Min Act: -0.1700

Data Index: 5604821 (Open Web Text)

Max Activating Token Index: 14

Text #6

Max Range: 2.3231. Min Range: -2.3231

Max Act: 2.1470. Min Act: -0.1700

Data Index: 6067547 (Open Web Text)

Max Activating Token Index: 623

Text #7

Max Range: 2.3231. Min Range: -2.3231

Max Act: 2.1573. Min Act: -0.1700

Data Index: 3286161 (Open Web Text)

Max Activating Token Index: 337

Text #8

Max Range: 2.3231. Min Range: -2.3231

Max Act: 2.1463. Min Act: -0.1700

Data Index: 4134181 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 2.3231. Min Range: -2.3231

Max Act: 2.1267. Min Act: -0.1700

Data Index: 8382552 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 2.3231. Min Range: -2.3231

Max Act: 2.1156. Min Act: -0.1700

Data Index: 4361612 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 2.3231. Min Range: -2.3231

Max Act: 2.1118. Min Act: -0.1700

Data Index: 6654701 (Open Web Text)

Max Activating Token Index: 855

Text #12

Max Range: 2.3231. Min Range: -2.3231

Max Act: 2.1270. Min Act: -0.1700

Data Index: 7888082 (Open Web Text)

Max Activating Token Index: 420

Text #13

Max Range: 2.3231. Min Range: -2.3231

Max Act: 2.1141. Min Act: -0.1700

Data Index: 6348355 (Open Web Text)

Max Activating Token Index: 210

Text #14

Max Range: 2.3231. Min Range: -2.3231

Max Act: 2.1221. Min Act: -0.1700

Data Index: 7891240 (Open Web Text)

Max Activating Token Index: 742

Text #15

Max Range: 2.3231. Min Range: -2.3231

Max Act: 2.0989. Min Act: -0.1700

Data Index: 6904294 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 2.3231. Min Range: -2.3231

Max Act: 2.1079. Min Act: -0.1700

Data Index: 790443 (Open Web Text)

Max Activating Token Index: 940

Text #17

Max Range: 2.3231. Min Range: -2.3231

Max Act: 2.0935. Min Act: -0.1700

Data Index: 817017 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 2.3231. Min Range: -2.3231

Max Act: 2.1042. Min Act: -0.1700

Data Index: 4148021 (Open Web Text)

Max Activating Token Index: 514

Text #19

Max Range: 2.3231. Min Range: -2.3231

Max Act: 2.0876. Min Act: -0.1700

Data Index: 3545787 (Open Web Text)

Max Activating Token Index: 809