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

Dataset: Open Web Text

Neuron 3018 in Layer 0

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: 4.2167. Min Range: -4.2167

Max Act: 4.2167. Min Act: -0.1700

Data Index: 2246635 (Open Web Text)

Max Activating Token Index: 11

Text #1

Max Range: 4.2167. Min Range: -4.2167

Max Act: 3.9952. Min Act: -0.1700

Data Index: 468558 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 4.2167. Min Range: -4.2167

Max Act: 3.9527. Min Act: -0.1700

Data Index: 5696465 (Open Web Text)

Max Activating Token Index: 14

Text #3

Max Range: 4.2167. Min Range: -4.2167

Max Act: 3.9554. Min Act: -0.1700

Data Index: 497272 (Open Web Text)

Max Activating Token Index: 40

Text #4

Max Range: 4.2167. Min Range: -4.2167

Max Act: 3.9253. Min Act: -0.1700

Data Index: 4800544 (Open Web Text)

Max Activating Token Index: 717

Text #5

Max Range: 4.2167. Min Range: -4.2167

Max Act: 3.9189. Min Act: -0.1700

Data Index: 2636972 (Open Web Text)

Max Activating Token Index: 102

Text #6

Max Range: 4.2167. Min Range: -4.2167

Max Act: 3.8904. Min Act: -0.1700

Data Index: 816881 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 4.2167. Min Range: -4.2167

Max Act: 3.8900. Min Act: -0.1700

Data Index: 1100406 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 4.2167. Min Range: -4.2167

Max Act: 3.8837. Min Act: -0.1700

Data Index: 2874455 (Open Web Text)

Max Activating Token Index: 38

Text #9

Max Range: 4.2167. Min Range: -4.2167

Max Act: 3.8558. Min Act: -0.1700

Data Index: 3968097 (Open Web Text)

Max Activating Token Index: 369

Text #10

Max Range: 4.2167. Min Range: -4.2167

Max Act: 3.8871. Min Act: -0.1700

Data Index: 4664253 (Open Web Text)

Max Activating Token Index: 533

Text #11

Max Range: 4.2167. Min Range: -4.2167

Max Act: 3.8559. Min Act: -0.1700

Data Index: 3040645 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 4.2167. Min Range: -4.2167

Max Act: 3.8891. Min Act: -0.1700

Data Index: 1842721 (Open Web Text)

Max Activating Token Index: 971

Text #13

Max Range: 4.2167. Min Range: -4.2167

Max Act: 3.8543. Min Act: -0.1700

Data Index: 5080714 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 4.2167. Min Range: -4.2167

Max Act: 3.8628. Min Act: -0.1700

Data Index: 4668626 (Open Web Text)

Max Activating Token Index: 55

Text #15

Max Range: 4.2167. Min Range: -4.2167

Max Act: 3.8615. Min Act: -0.1700

Data Index: 296219 (Open Web Text)

Max Activating Token Index: 53

Text #16

Max Range: 4.2167. Min Range: -4.2167

Max Act: 3.8295. Min Act: -0.1700

Data Index: 3524851 (Open Web Text)

Max Activating Token Index: 46

Text #17

Max Range: 4.2167. Min Range: -4.2167

Max Act: 3.8488. Min Act: -0.1700

Data Index: 3935754 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 4.2167. Min Range: -4.2167

Max Act: 3.8302. Min Act: -0.1700

Data Index: 6196376 (Open Web Text)

Max Activating Token Index: 247

Text #19

Max Range: 4.2167. Min Range: -4.2167

Max Act: 3.8417. Min Act: -0.1700

Data Index: 1404540 (Open Web Text)

Max Activating Token Index: 829