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

Dataset: Open Web Text

Neuron 2670 in Layer 3

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: 4.4518. Min Range: -4.4518

Max Act: 4.4518. Min Act: -0.1700

Data Index: 1950874 (Open Web Text)

Max Activating Token Index: 60

Text #1

Max Range: 4.4518. Min Range: -4.4518

Max Act: 4.4191. Min Act: -0.1700

Data Index: 1711105 (Open Web Text)

Max Activating Token Index: 106

Text #2

Max Range: 4.4518. Min Range: -4.4518

Max Act: 4.3016. Min Act: -0.1700

Data Index: 3675582 (Open Web Text)

Max Activating Token Index: 22

Text #3

Max Range: 4.4518. Min Range: -4.4518

Max Act: 4.3286. Min Act: -0.1700

Data Index: 6414896 (Open Web Text)

Max Activating Token Index: 248

Text #4

Max Range: 4.4518. Min Range: -4.4518

Max Act: 4.2367. Min Act: -0.1700

Data Index: 4245661 (Open Web Text)

Max Activating Token Index: 116

Text #5

Max Range: 4.4518. Min Range: -4.4518

Max Act: 4.2992. Min Act: -0.1700

Data Index: 1265609 (Open Web Text)

Max Activating Token Index: 888

Text #6

Max Range: 4.4518. Min Range: -4.4518

Max Act: 4.2488. Min Act: -0.1700

Data Index: 467549 (Open Web Text)

Max Activating Token Index: 551

Text #7

Max Range: 4.4518. Min Range: -4.4518

Max Act: 4.2359. Min Act: -0.1700

Data Index: 1726363 (Open Web Text)

Max Activating Token Index: 330

Text #8

Max Range: 4.4518. Min Range: -4.4518

Max Act: 4.1948. Min Act: -0.1700

Data Index: 5312580 (Open Web Text)

Max Activating Token Index: 342

Text #9

Max Range: 4.4518. Min Range: -4.4518

Max Act: 4.2190. Min Act: -0.1700

Data Index: 5658800 (Open Web Text)

Max Activating Token Index: 529

Text #10

Max Range: 4.4518. Min Range: -4.4518

Max Act: 4.1189. Min Act: -0.1700

Data Index: 589178 (Open Web Text)

Max Activating Token Index: 117

Text #11

Max Range: 4.4518. Min Range: -4.4518

Max Act: 4.1459. Min Act: -0.1700

Data Index: 2438448 (Open Web Text)

Max Activating Token Index: 451

Text #12

Max Range: 4.4518. Min Range: -4.4518

Max Act: 4.1682. Min Act: -0.1700

Data Index: 5312579 (Open Web Text)

Max Activating Token Index: 183

Text #13

Max Range: 4.4518. Min Range: -4.4518

Max Act: 4.1355. Min Act: -0.1700

Data Index: 2017696 (Open Web Text)

Max Activating Token Index: 502

Text #14

Max Range: 4.4518. Min Range: -4.4518

Max Act: 4.0972. Min Act: -0.1700

Data Index: 8606281 (Open Web Text)

Max Activating Token Index: 501

Text #15

Max Range: 4.4518. Min Range: -4.4518

Max Act: 4.0844. Min Act: -0.1700

Data Index: 8128326 (Open Web Text)

Max Activating Token Index: 593

Text #16

Max Range: 4.4518. Min Range: -4.4518

Max Act: 4.1136. Min Act: -0.1700

Data Index: 2795771 (Open Web Text)

Max Activating Token Index: 654

Text #17

Max Range: 4.4518. Min Range: -4.4518

Max Act: 4.1124. Min Act: -0.1700

Data Index: 4928413 (Open Web Text)

Max Activating Token Index: 435

Text #18

Max Range: 4.4518. Min Range: -4.4518

Max Act: 4.0985. Min Act: -0.1700

Data Index: 2706870 (Open Web Text)

Max Activating Token Index: 30

Text #19

Max Range: 4.4518. Min Range: -4.4518

Max Act: 4.0888. Min Act: -0.1700

Data Index: 3794153 (Open Web Text)

Max Activating Token Index: 197