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

Dataset: Open Web Text

Neuron 1602 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: 3.3881. Min Range: -3.3881

Max Act: 3.3881. Min Act: -0.1700

Data Index: 3857283 (Open Web Text)

Max Activating Token Index: 633

Text #1

Max Range: 3.3881. Min Range: -3.3881

Max Act: 3.3169. Min Act: -0.1700

Data Index: 7979401 (Open Web Text)

Max Activating Token Index: 495

Text #2

Max Range: 3.3881. Min Range: -3.3881

Max Act: 3.2155. Min Act: -0.1700

Data Index: 6613756 (Open Web Text)

Max Activating Token Index: 362

Text #3

Max Range: 3.3881. Min Range: -3.3881

Max Act: 3.1928. Min Act: -0.1700

Data Index: 4957276 (Open Web Text)

Max Activating Token Index: 91

Text #4

Max Range: 3.3881. Min Range: -3.3881

Max Act: 3.1941. Min Act: -0.1700

Data Index: 4250544 (Open Web Text)

Max Activating Token Index: 352

Text #5

Max Range: 3.3881. Min Range: -3.3881

Max Act: 3.1808. Min Act: -0.1700

Data Index: 2559286 (Open Web Text)

Max Activating Token Index: 95

Text #6

Max Range: 3.3881. Min Range: -3.3881

Max Act: 3.1820. Min Act: -0.1700

Data Index: 2204558 (Open Web Text)

Max Activating Token Index: 939

Text #7

Max Range: 3.3881. Min Range: -3.3881

Max Act: 3.1499. Min Act: -0.1700

Data Index: 4098232 (Open Web Text)

Max Activating Token Index: 717

Text #8

Max Range: 3.3881. Min Range: -3.3881

Max Act: 3.1562. Min Act: -0.1700

Data Index: 154159 (Open Web Text)

Max Activating Token Index: 620

Text #9

Max Range: 3.3881. Min Range: -3.3881

Max Act: 3.1764. Min Act: -0.1700

Data Index: 5505965 (Open Web Text)

Max Activating Token Index: 308

Text #10

Max Range: 3.3881. Min Range: -3.3881

Max Act: 3.1519. Min Act: -0.1700

Data Index: 3503330 (Open Web Text)

Max Activating Token Index: 455

Text #11

Max Range: 3.3881. Min Range: -3.3881

Max Act: 3.1444. Min Act: -0.1700

Data Index: 8148650 (Open Web Text)

Max Activating Token Index: 114

Text #12

Max Range: 3.3881. Min Range: -3.3881

Max Act: 3.1303. Min Act: -0.1700

Data Index: 2899391 (Open Web Text)

Max Activating Token Index: 1008

Text #13

Max Range: 3.3881. Min Range: -3.3881

Max Act: 3.1552. Min Act: -0.1700

Data Index: 7044925 (Open Web Text)

Max Activating Token Index: 897

Text #14

Max Range: 3.3881. Min Range: -3.3881

Max Act: 3.1406. Min Act: -0.1700

Data Index: 2783333 (Open Web Text)

Max Activating Token Index: 42

Text #15

Max Range: 3.3881. Min Range: -3.3881

Max Act: 3.1335. Min Act: -0.1700

Data Index: 2735884 (Open Web Text)

Max Activating Token Index: 551

Text #16

Max Range: 3.3881. Min Range: -3.3881

Max Act: 3.1382. Min Act: -0.1700

Data Index: 8586367 (Open Web Text)

Max Activating Token Index: 250

Text #17

Max Range: 3.3881. Min Range: -3.3881

Max Act: 3.1398. Min Act: -0.1700

Data Index: 3756772 (Open Web Text)

Max Activating Token Index: 120

Text #18

Max Range: 3.3881. Min Range: -3.3881

Max Act: 3.1281. Min Act: -0.1700

Data Index: 6712392 (Open Web Text)

Max Activating Token Index: 406

Text #19

Max Range: 3.3881. Min Range: -3.3881

Max Act: 3.1183. Min Act: -0.1700

Data Index: 2004269 (Open Web Text)

Max Activating Token Index: 417