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

Dataset: Open Web Text

Neuron 186 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: 3.8547. Min Range: -3.8547

Max Act: 3.8547. Min Act: -0.1700

Data Index: 4520174 (Open Web Text)

Max Activating Token Index: 628

Text #1

Max Range: 3.8547. Min Range: -3.8547

Max Act: 3.7870. Min Act: -0.1700

Data Index: 2647643 (Open Web Text)

Max Activating Token Index: 471

Text #2

Max Range: 3.8547. Min Range: -3.8547

Max Act: 3.7838. Min Act: -0.1700

Data Index: 1655302 (Open Web Text)

Max Activating Token Index: 280

Text #3

Max Range: 3.8547. Min Range: -3.8547

Max Act: 3.7895. Min Act: -0.1700

Data Index: 3527604 (Open Web Text)

Max Activating Token Index: 12

Text #4

Max Range: 3.8547. Min Range: -3.8547

Max Act: 3.7925. Min Act: -0.1700

Data Index: 277141 (Open Web Text)

Max Activating Token Index: 272

Text #5

Max Range: 3.8547. Min Range: -3.8547

Max Act: 3.7236. Min Act: -0.1700

Data Index: 3363131 (Open Web Text)

Max Activating Token Index: 14

Text #6

Max Range: 3.8547. Min Range: -3.8547

Max Act: 3.7249. Min Act: -0.1700

Data Index: 519570 (Open Web Text)

Max Activating Token Index: 178

Text #7

Max Range: 3.8547. Min Range: -3.8547

Max Act: 3.7143. Min Act: -0.1700

Data Index: 2595485 (Open Web Text)

Max Activating Token Index: 609

Text #8

Max Range: 3.8547. Min Range: -3.8547

Max Act: 3.7036. Min Act: -0.1700

Data Index: 8105337 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 3.8547. Min Range: -3.8547

Max Act: 3.7110. Min Act: -0.1700

Data Index: 7996601 (Open Web Text)

Max Activating Token Index: 113

Text #10

Max Range: 3.8547. Min Range: -3.8547

Max Act: 3.7603. Min Act: -0.1700

Data Index: 6685044 (Open Web Text)

Max Activating Token Index: 468

Text #11

Max Range: 3.8547. Min Range: -3.8547

Max Act: 3.6403. Min Act: -0.1700

Data Index: 4166567 (Open Web Text)

Max Activating Token Index: 476

Text #12

Max Range: 3.8547. Min Range: -3.8547

Max Act: 3.6723. Min Act: -0.1700

Data Index: 626078 (Open Web Text)

Max Activating Token Index: 369

Text #13

Max Range: 3.8547. Min Range: -3.8547

Max Act: 3.6792. Min Act: -0.1700

Data Index: 7863357 (Open Web Text)

Max Activating Token Index: 568

Text #14

Max Range: 3.8547. Min Range: -3.8547

Max Act: 3.6778. Min Act: -0.1700

Data Index: 6673738 (Open Web Text)

Max Activating Token Index: 14

Text #15

Max Range: 3.8547. Min Range: -3.8547

Max Act: 3.6887. Min Act: -0.1700

Data Index: 859784 (Open Web Text)

Max Activating Token Index: 332

Text #16

Max Range: 3.8547. Min Range: -3.8547

Max Act: 3.6859. Min Act: -0.1700

Data Index: 3763359 (Open Web Text)

Max Activating Token Index: 981

Text #17

Max Range: 3.8547. Min Range: -3.8547

Max Act: 3.6713. Min Act: -0.1700

Data Index: 28058 (Open Web Text)

Max Activating Token Index: 11

Text #18

Max Range: 3.8547. Min Range: -3.8547

Max Act: 3.6744. Min Act: -0.1700

Data Index: 3420135 (Open Web Text)

Max Activating Token Index: 374

Text #19

Max Range: 3.8547. Min Range: -3.8547

Max Act: 3.6416. Min Act: -0.1700

Data Index: 998516 (Open Web Text)

Max Activating Token Index: 977