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

Dataset: Open Web Text

Neuron 2152 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: 3.4259. Min Range: -3.4259

Max Act: 3.4259. Min Act: -0.1700

Data Index: 8748936 (Open Web Text)

Max Activating Token Index: 202

Text #1

Max Range: 3.4259. Min Range: -3.4259

Max Act: 3.3442. Min Act: -0.1700

Data Index: 5787065 (Open Web Text)

Max Activating Token Index: 543

Text #2

Max Range: 3.4259. Min Range: -3.4259

Max Act: 3.2749. Min Act: -0.1700

Data Index: 1155288 (Open Web Text)

Max Activating Token Index: 145

Text #3

Max Range: 3.4259. Min Range: -3.4259

Max Act: 3.2775. Min Act: -0.1700

Data Index: 5906737 (Open Web Text)

Max Activating Token Index: 245

Text #4

Max Range: 3.4259. Min Range: -3.4259

Max Act: 3.2493. Min Act: -0.1700

Data Index: 2438170 (Open Web Text)

Max Activating Token Index: 501

Text #5

Max Range: 3.4259. Min Range: -3.4259

Max Act: 3.2282. Min Act: -0.1700

Data Index: 6994698 (Open Web Text)

Max Activating Token Index: 827

Text #6

Max Range: 3.4259. Min Range: -3.4259

Max Act: 3.2187. Min Act: -0.1700

Data Index: 7886985 (Open Web Text)

Max Activating Token Index: 359

Text #7

Max Range: 3.4259. Min Range: -3.4259

Max Act: 3.2136. Min Act: -0.1700

Data Index: 7554558 (Open Web Text)

Max Activating Token Index: 320

Text #8

Max Range: 3.4259. Min Range: -3.4259

Max Act: 3.2358. Min Act: -0.1700

Data Index: 2405013 (Open Web Text)

Max Activating Token Index: 1006

Text #9

Max Range: 3.4259. Min Range: -3.4259

Max Act: 3.2073. Min Act: -0.1700

Data Index: 6596496 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 3.4259. Min Range: -3.4259

Max Act: 3.1964. Min Act: -0.1700

Data Index: 3454714 (Open Web Text)

Max Activating Token Index: 526

Text #11

Max Range: 3.4259. Min Range: -3.4259

Max Act: 3.2078. Min Act: -0.1700

Data Index: 4248438 (Open Web Text)

Max Activating Token Index: 998

Text #12

Max Range: 3.4259. Min Range: -3.4259

Max Act: 3.1931. Min Act: -0.1700

Data Index: 7537624 (Open Web Text)

Max Activating Token Index: 348

Text #13

Max Range: 3.4259. Min Range: -3.4259

Max Act: 3.1848. Min Act: -0.1700

Data Index: 7939193 (Open Web Text)

Max Activating Token Index: 850

Text #14

Max Range: 3.4259. Min Range: -3.4259

Max Act: 3.1676. Min Act: -0.1700

Data Index: 7530789 (Open Web Text)

Max Activating Token Index: 894

Text #15

Max Range: 3.4259. Min Range: -3.4259

Max Act: 3.1398. Min Act: -0.1700

Data Index: 2567621 (Open Web Text)

Max Activating Token Index: 518

Text #16

Max Range: 3.4259. Min Range: -3.4259

Max Act: 3.1470. Min Act: -0.1700

Data Index: 6280249 (Open Web Text)

Max Activating Token Index: 654

Text #17

Max Range: 3.4259. Min Range: -3.4259

Max Act: 3.1050. Min Act: -0.1700

Data Index: 1382675 (Open Web Text)

Max Activating Token Index: 552

Text #18

Max Range: 3.4259. Min Range: -3.4259

Max Act: 3.1191. Min Act: -0.1700

Data Index: 1060619 (Open Web Text)

Max Activating Token Index: 21

Text #19

Max Range: 3.4259. Min Range: -3.4259

Max Act: 3.1033. Min Act: -0.1700

Data Index: 823853 (Open Web Text)

Max Activating Token Index: 898