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

Dataset: Open Web Text

Neuron 580 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: 5.1174. Min Range: -5.1174

Max Act: 5.1016. Min Act: -0.1700

Data Index: 1050252 (Open Web Text)

Max Activating Token Index: 93

Text #1

Max Range: 5.1174. Min Range: -5.1174

Max Act: 5.1174. Min Act: -0.1700

Data Index: 6276408 (Open Web Text)

Max Activating Token Index: 924

Text #2

Max Range: 5.1174. Min Range: -5.1174

Max Act: 5.0915. Min Act: -0.1700

Data Index: 7988222 (Open Web Text)

Max Activating Token Index: 971

Text #3

Max Range: 5.1174. Min Range: -5.1174

Max Act: 5.0304. Min Act: -0.1700

Data Index: 736906 (Open Web Text)

Max Activating Token Index: 669

Text #4

Max Range: 5.1174. Min Range: -5.1174

Max Act: 5.0306. Min Act: -0.1700

Data Index: 2433096 (Open Web Text)

Max Activating Token Index: 873

Text #5

Max Range: 5.1174. Min Range: -5.1174

Max Act: 5.0313. Min Act: -0.1700

Data Index: 2663559 (Open Web Text)

Max Activating Token Index: 847

Text #6

Max Range: 5.1174. Min Range: -5.1174

Max Act: 4.9659. Min Act: -0.1700

Data Index: 2368357 (Open Web Text)

Max Activating Token Index: 756

Text #7

Max Range: 5.1174. Min Range: -5.1174

Max Act: 4.9745. Min Act: -0.1700

Data Index: 5155581 (Open Web Text)

Max Activating Token Index: 244

Text #8

Max Range: 5.1174. Min Range: -5.1174

Max Act: 5.0130. Min Act: -0.1700

Data Index: 5243709 (Open Web Text)

Max Activating Token Index: 358

Text #9

Max Range: 5.1174. Min Range: -5.1174

Max Act: 5.0006. Min Act: -0.1700

Data Index: 4723160 (Open Web Text)

Max Activating Token Index: 36

Text #10

Max Range: 5.1174. Min Range: -5.1174

Max Act: 4.9293. Min Act: -0.1700

Data Index: 6274933 (Open Web Text)

Max Activating Token Index: 86

Text #11

Max Range: 5.1174. Min Range: -5.1174

Max Act: 4.9492. Min Act: -0.1700

Data Index: 471576 (Open Web Text)

Max Activating Token Index: 474

Text #12

Max Range: 5.1174. Min Range: -5.1174

Max Act: 4.9233. Min Act: -0.1700

Data Index: 621313 (Open Web Text)

Max Activating Token Index: 307

Text #13

Max Range: 5.1174. Min Range: -5.1174

Max Act: 4.9028. Min Act: -0.1700

Data Index: 7391381 (Open Web Text)

Max Activating Token Index: 675

Text #14

Max Range: 5.1174. Min Range: -5.1174

Max Act: 4.8722. Min Act: -0.1700

Data Index: 3381438 (Open Web Text)

Max Activating Token Index: 922

Text #15

Max Range: 5.1174. Min Range: -5.1174

Max Act: 4.9240. Min Act: -0.1700

Data Index: 8134025 (Open Web Text)

Max Activating Token Index: 980

Text #16

Max Range: 5.1174. Min Range: -5.1174

Max Act: 4.8795. Min Act: -0.1700

Data Index: 7231615 (Open Web Text)

Max Activating Token Index: 369

Text #17

Max Range: 5.1174. Min Range: -5.1174

Max Act: 4.8858. Min Act: -0.1700

Data Index: 4171954 (Open Web Text)

Max Activating Token Index: 473

Text #18

Max Range: 5.1174. Min Range: -5.1174

Max Act: 4.8930. Min Act: -0.1700

Data Index: 6856537 (Open Web Text)

Max Activating Token Index: 155

Text #19

Max Range: 5.1174. Min Range: -5.1174

Max Act: 4.8630. Min Act: -0.1700

Data Index: 2298345 (Open Web Text)

Max Activating Token Index: 910