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

Dataset: Open Web Text

Neuron 1313 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: 4.3137. Min Range: -4.3137

Max Act: 4.3137. Min Act: -0.1700

Data Index: 7824459 (Open Web Text)

Max Activating Token Index: 1010

Text #1

Max Range: 4.3137. Min Range: -4.3137

Max Act: 4.2724. Min Act: -0.1700

Data Index: 6456047 (Open Web Text)

Max Activating Token Index: 424

Text #2

Max Range: 4.3137. Min Range: -4.3137

Max Act: 4.2333. Min Act: -0.1700

Data Index: 4783371 (Open Web Text)

Max Activating Token Index: 140

Text #3

Max Range: 4.3137. Min Range: -4.3137

Max Act: 4.2592. Min Act: -0.1700

Data Index: 2535951 (Open Web Text)

Max Activating Token Index: 864

Text #4

Max Range: 4.3137. Min Range: -4.3137

Max Act: 4.2246. Min Act: -0.1700

Data Index: 8230854 (Open Web Text)

Max Activating Token Index: 497

Text #5

Max Range: 4.3137. Min Range: -4.3137

Max Act: 4.2014. Min Act: -0.1700

Data Index: 4159461 (Open Web Text)

Max Activating Token Index: 311

Text #6

Max Range: 4.3137. Min Range: -4.3137

Max Act: 4.1875. Min Act: -0.1700

Data Index: 789120 (Open Web Text)

Max Activating Token Index: 833

Text #7

Max Range: 4.3137. Min Range: -4.3137

Max Act: 4.1783. Min Act: -0.1700

Data Index: 1870710 (Open Web Text)

Max Activating Token Index: 319

Text #8

Max Range: 4.3137. Min Range: -4.3137

Max Act: 4.2053. Min Act: -0.1700

Data Index: 2861293 (Open Web Text)

Max Activating Token Index: 940

Text #9

Max Range: 4.3137. Min Range: -4.3137

Max Act: 4.1285. Min Act: -0.1700

Data Index: 3898251 (Open Web Text)

Max Activating Token Index: 625

Text #10

Max Range: 4.3137. Min Range: -4.3137

Max Act: 4.1079. Min Act: -0.1700

Data Index: 7343180 (Open Web Text)

Max Activating Token Index: 305

Text #11

Max Range: 4.3137. Min Range: -4.3137

Max Act: 4.1312. Min Act: -0.1700

Data Index: 3916553 (Open Web Text)

Max Activating Token Index: 967

Text #12

Max Range: 4.3137. Min Range: -4.3137

Max Act: 4.1242. Min Act: -0.1700

Data Index: 6807226 (Open Web Text)

Max Activating Token Index: 73

Text #13

Max Range: 4.3137. Min Range: -4.3137

Max Act: 4.1031. Min Act: -0.1700

Data Index: 1235083 (Open Web Text)

Max Activating Token Index: 953

Text #14

Max Range: 4.3137. Min Range: -4.3137

Max Act: 4.1334. Min Act: -0.1700

Data Index: 1196311 (Open Web Text)

Max Activating Token Index: 856

Text #15

Max Range: 4.3137. Min Range: -4.3137

Max Act: 4.1169. Min Act: -0.1700

Data Index: 2794637 (Open Web Text)

Max Activating Token Index: 489

Text #16

Max Range: 4.3137. Min Range: -4.3137

Max Act: 4.1458. Min Act: -0.1700

Data Index: 8755734 (Open Web Text)

Max Activating Token Index: 810

Text #17

Max Range: 4.3137. Min Range: -4.3137

Max Act: 4.0897. Min Act: -0.1700

Data Index: 6590366 (Open Web Text)

Max Activating Token Index: 451

Text #18

Max Range: 4.3137. Min Range: -4.3137

Max Act: 4.0858. Min Act: -0.1700

Data Index: 3913894 (Open Web Text)

Max Activating Token Index: 584

Text #19

Max Range: 4.3137. Min Range: -4.3137

Max Act: 4.0878. Min Act: -0.1700

Data Index: 6460039 (Open Web Text)

Max Activating Token Index: 486