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

Dataset: Open Web Text

Neuron 1276 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: 4.4330. Min Range: -4.4330

Max Act: 4.4330. Min Act: -0.1700

Data Index: 8023280 (Open Web Text)

Max Activating Token Index: 646

Text #1

Max Range: 4.4330. Min Range: -4.4330

Max Act: 4.3283. Min Act: -0.1700

Data Index: 5278340 (Open Web Text)

Max Activating Token Index: 428

Text #2

Max Range: 4.4330. Min Range: -4.4330

Max Act: 4.3250. Min Act: -0.1700

Data Index: 5638193 (Open Web Text)

Max Activating Token Index: 688

Text #3

Max Range: 4.4330. Min Range: -4.4330

Max Act: 4.2171. Min Act: -0.1700

Data Index: 8668473 (Open Web Text)

Max Activating Token Index: 217

Text #4

Max Range: 4.4330. Min Range: -4.4330

Max Act: 4.1952. Min Act: -0.1700

Data Index: 3814677 (Open Web Text)

Max Activating Token Index: 801

Text #5

Max Range: 4.4330. Min Range: -4.4330

Max Act: 4.1876. Min Act: -0.1700

Data Index: 7739993 (Open Web Text)

Max Activating Token Index: 676

Text #6

Max Range: 4.4330. Min Range: -4.4330

Max Act: 4.1541. Min Act: -0.1700

Data Index: 1927396 (Open Web Text)

Max Activating Token Index: 1021

Text #7

Max Range: 4.4330. Min Range: -4.4330

Max Act: 4.1396. Min Act: -0.1700

Data Index: 7945314 (Open Web Text)

Max Activating Token Index: 873

Text #8

Max Range: 4.4330. Min Range: -4.4330

Max Act: 4.1759. Min Act: -0.1700

Data Index: 5592175 (Open Web Text)

Max Activating Token Index: 871

Text #9

Max Range: 4.4330. Min Range: -4.4330

Max Act: 4.1247. Min Act: -0.1700

Data Index: 4085190 (Open Web Text)

Max Activating Token Index: 186

Text #10

Max Range: 4.4330. Min Range: -4.4330

Max Act: 4.1247. Min Act: -0.1700

Data Index: 2429664 (Open Web Text)

Max Activating Token Index: 310

Text #11

Max Range: 4.4330. Min Range: -4.4330

Max Act: 4.1061. Min Act: -0.1700

Data Index: 2165964 (Open Web Text)

Max Activating Token Index: 116

Text #12

Max Range: 4.4330. Min Range: -4.4330

Max Act: 4.1441. Min Act: -0.1700

Data Index: 4125754 (Open Web Text)

Max Activating Token Index: 397

Text #13

Max Range: 4.4330. Min Range: -4.4330

Max Act: 4.1398. Min Act: -0.1700

Data Index: 5018079 (Open Web Text)

Max Activating Token Index: 531

Text #14

Max Range: 4.4330. Min Range: -4.4330

Max Act: 4.1086. Min Act: -0.1700

Data Index: 2099571 (Open Web Text)

Max Activating Token Index: 857

Text #15

Max Range: 4.4330. Min Range: -4.4330

Max Act: 4.1339. Min Act: -0.1700

Data Index: 8158879 (Open Web Text)

Max Activating Token Index: 386

Text #16

Max Range: 4.4330. Min Range: -4.4330

Max Act: 4.1201. Min Act: -0.1700

Data Index: 3231507 (Open Web Text)

Max Activating Token Index: 391

Text #17

Max Range: 4.4330. Min Range: -4.4330

Max Act: 4.1497. Min Act: -0.1700

Data Index: 5699727 (Open Web Text)

Max Activating Token Index: 617

Text #18

Max Range: 4.4330. Min Range: -4.4330

Max Act: 4.1092. Min Act: -0.1700

Data Index: 6997100 (Open Web Text)

Max Activating Token Index: 330

Text #19

Max Range: 4.4330. Min Range: -4.4330

Max Act: 4.1385. Min Act: -0.1700

Data Index: 6436644 (Open Web Text)

Max Activating Token Index: 727