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

Dataset: Open Web Text

Neuron 1655 in Layer 4

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: 3.4068. Min Range: -3.4068

Max Act: 3.4068. Min Act: -0.1700

Data Index: 7713578 (Open Web Text)

Max Activating Token Index: 356

Text #1

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.2696. Min Act: -0.1700

Data Index: 1748321 (Open Web Text)

Max Activating Token Index: 747

Text #2

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.1855. Min Act: -0.1700

Data Index: 2451196 (Open Web Text)

Max Activating Token Index: 53

Text #3

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.2184. Min Act: -0.1700

Data Index: 6574601 (Open Web Text)

Max Activating Token Index: 390

Text #4

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.1827. Min Act: -0.1700

Data Index: 1096315 (Open Web Text)

Max Activating Token Index: 661

Text #5

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.1943. Min Act: -0.1700

Data Index: 3604059 (Open Web Text)

Max Activating Token Index: 311

Text #6

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.1725. Min Act: -0.1700

Data Index: 2714650 (Open Web Text)

Max Activating Token Index: 710

Text #7

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.1941. Min Act: -0.1700

Data Index: 5915362 (Open Web Text)

Max Activating Token Index: 900

Text #8

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.1481. Min Act: -0.1700

Data Index: 4712298 (Open Web Text)

Max Activating Token Index: 442

Text #9

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.1613. Min Act: -0.1700

Data Index: 5401875 (Open Web Text)

Max Activating Token Index: 246

Text #10

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.1646. Min Act: -0.1700

Data Index: 759741 (Open Web Text)

Max Activating Token Index: 1006

Text #11

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.1400. Min Act: -0.1700

Data Index: 3837885 (Open Web Text)

Max Activating Token Index: 887

Text #12

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.1399. Min Act: -0.1700

Data Index: 7821338 (Open Web Text)

Max Activating Token Index: 658

Text #13

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.1448. Min Act: -0.1700

Data Index: 7915325 (Open Web Text)

Max Activating Token Index: 969

Text #14

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.1539. Min Act: -0.1700

Data Index: 8214432 (Open Web Text)

Max Activating Token Index: 652

Text #15

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.1417. Min Act: -0.1700

Data Index: 5219498 (Open Web Text)

Max Activating Token Index: 238

Text #16

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.1121. Min Act: -0.1700

Data Index: 7449143 (Open Web Text)

Max Activating Token Index: 946

Text #17

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.1199. Min Act: -0.1700

Data Index: 489954 (Open Web Text)

Max Activating Token Index: 751

Text #18

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.1279. Min Act: -0.1700

Data Index: 2697918 (Open Web Text)

Max Activating Token Index: 852

Text #19

Max Range: 3.4068. Min Range: -3.4068

Max Act: 3.1329. Min Act: -0.1700

Data Index: 8285075 (Open Web Text)

Max Activating Token Index: 970