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

Dataset: Open Web Text

Neuron 1530 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: 4.1963. Min Range: -4.1963

Max Act: 4.1892. Min Act: -0.1700

Data Index: 2721917 (Open Web Text)

Max Activating Token Index: 293

Text #1

Max Range: 4.1963. Min Range: -4.1963

Max Act: 4.1742. Min Act: -0.1700

Data Index: 6341833 (Open Web Text)

Max Activating Token Index: 904

Text #2

Max Range: 4.1963. Min Range: -4.1963

Max Act: 4.1963. Min Act: -0.1700

Data Index: 7470062 (Open Web Text)

Max Activating Token Index: 271

Text #3

Max Range: 4.1963. Min Range: -4.1963

Max Act: 4.1714. Min Act: -0.1700

Data Index: 7919327 (Open Web Text)

Max Activating Token Index: 125

Text #4

Max Range: 4.1963. Min Range: -4.1963

Max Act: 4.1764. Min Act: -0.1700

Data Index: 4982037 (Open Web Text)

Max Activating Token Index: 276

Text #5

Max Range: 4.1963. Min Range: -4.1963

Max Act: 4.1777. Min Act: -0.1700

Data Index: 3615384 (Open Web Text)

Max Activating Token Index: 257

Text #6

Max Range: 4.1963. Min Range: -4.1963

Max Act: 4.1932. Min Act: -0.1700

Data Index: 6219965 (Open Web Text)

Max Activating Token Index: 464

Text #7

Max Range: 4.1963. Min Range: -4.1963

Max Act: 4.1843. Min Act: -0.1700

Data Index: 6549222 (Open Web Text)

Max Activating Token Index: 735

Text #8

Max Range: 4.1963. Min Range: -4.1963

Max Act: 4.1630. Min Act: -0.1700

Data Index: 6619031 (Open Web Text)

Max Activating Token Index: 987

Text #9

Max Range: 4.1963. Min Range: -4.1963

Max Act: 4.1593. Min Act: -0.1700

Data Index: 2963269 (Open Web Text)

Max Activating Token Index: 281

Text #10

Max Range: 4.1963. Min Range: -4.1963

Max Act: 4.1477. Min Act: -0.1700

Data Index: 7708964 (Open Web Text)

Max Activating Token Index: 821

Text #11

Max Range: 4.1963. Min Range: -4.1963

Max Act: 4.1065. Min Act: -0.1700

Data Index: 4218805 (Open Web Text)

Max Activating Token Index: 461

Text #12

Max Range: 4.1963. Min Range: -4.1963

Max Act: 4.1381. Min Act: -0.1700

Data Index: 117583 (Open Web Text)

Max Activating Token Index: 797

Text #13

Max Range: 4.1963. Min Range: -4.1963

Max Act: 4.1490. Min Act: -0.1700

Data Index: 104905 (Open Web Text)

Max Activating Token Index: 379

Text #14

Max Range: 4.1963. Min Range: -4.1963

Max Act: 4.1310. Min Act: -0.1700

Data Index: 3794918 (Open Web Text)

Max Activating Token Index: 766

Text #15

Max Range: 4.1963. Min Range: -4.1963

Max Act: 4.1176. Min Act: -0.1700

Data Index: 1888101 (Open Web Text)

Max Activating Token Index: 702

Text #16

Max Range: 4.1963. Min Range: -4.1963

Max Act: 4.1231. Min Act: -0.1700

Data Index: 1568519 (Open Web Text)

Max Activating Token Index: 592

Text #17

Max Range: 4.1963. Min Range: -4.1963

Max Act: 4.1290. Min Act: -0.1700

Data Index: 3426776 (Open Web Text)

Max Activating Token Index: 236

Text #18

Max Range: 4.1963. Min Range: -4.1963

Max Act: 4.1224. Min Act: -0.1700

Data Index: 117528 (Open Web Text)

Max Activating Token Index: 366

Text #19

Max Range: 4.1963. Min Range: -4.1963

Max Act: 4.1659. Min Act: -0.1700

Data Index: 1561098 (Open Web Text)

Max Activating Token Index: 633