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

Dataset: Open Web Text

Neuron 2288 in Layer 1

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: 3.0255. Min Range: -3.0255

Max Act: 3.0255. Min Act: -0.1700

Data Index: 8468037 (Open Web Text)

Max Activating Token Index: 52

Text #1

Max Range: 3.0255. Min Range: -3.0255

Max Act: 2.9637. Min Act: -0.1700

Data Index: 5105645 (Open Web Text)

Max Activating Token Index: 16

Text #2

Max Range: 3.0255. Min Range: -3.0255

Max Act: 2.8685. Min Act: -0.1700

Data Index: 971365 (Open Web Text)

Max Activating Token Index: 159

Text #3

Max Range: 3.0255. Min Range: -3.0255

Max Act: 2.8708. Min Act: -0.1700

Data Index: 6253683 (Open Web Text)

Max Activating Token Index: 706

Text #4

Max Range: 3.0255. Min Range: -3.0255

Max Act: 2.8506. Min Act: -0.1700

Data Index: 7760565 (Open Web Text)

Max Activating Token Index: 461

Text #5

Max Range: 3.0255. Min Range: -3.0255

Max Act: 2.8436. Min Act: -0.1700

Data Index: 767274 (Open Web Text)

Max Activating Token Index: 355

Text #6

Max Range: 3.0255. Min Range: -3.0255

Max Act: 2.8294. Min Act: -0.1700

Data Index: 3090817 (Open Web Text)

Max Activating Token Index: 856

Text #7

Max Range: 3.0255. Min Range: -3.0255

Max Act: 2.8089. Min Act: -0.1700

Data Index: 5034941 (Open Web Text)

Max Activating Token Index: 274

Text #8

Max Range: 3.0255. Min Range: -3.0255

Max Act: 2.8233. Min Act: -0.1700

Data Index: 6979210 (Open Web Text)

Max Activating Token Index: 41

Text #9

Max Range: 3.0255. Min Range: -3.0255

Max Act: 2.8047. Min Act: -0.1700

Data Index: 8385581 (Open Web Text)

Max Activating Token Index: 113

Text #10

Max Range: 3.0255. Min Range: -3.0255

Max Act: 2.7828. Min Act: -0.1700

Data Index: 3116624 (Open Web Text)

Max Activating Token Index: 105

Text #11

Max Range: 3.0255. Min Range: -3.0255

Max Act: 2.7741. Min Act: -0.1700

Data Index: 2223674 (Open Web Text)

Max Activating Token Index: 806

Text #12

Max Range: 3.0255. Min Range: -3.0255

Max Act: 2.7766. Min Act: -0.1700

Data Index: 8680782 (Open Web Text)

Max Activating Token Index: 543

Text #13

Max Range: 3.0255. Min Range: -3.0255

Max Act: 2.7482. Min Act: -0.1700

Data Index: 5883895 (Open Web Text)

Max Activating Token Index: 166

Text #14

Max Range: 3.0255. Min Range: -3.0255

Max Act: 2.7442. Min Act: -0.1700

Data Index: 1769183 (Open Web Text)

Max Activating Token Index: 346

Text #15

Max Range: 3.0255. Min Range: -3.0255

Max Act: 2.7353. Min Act: -0.1700

Data Index: 6181495 (Open Web Text)

Max Activating Token Index: 107

Text #16

Max Range: 3.0255. Min Range: -3.0255

Max Act: 2.7424. Min Act: -0.1700

Data Index: 7172392 (Open Web Text)

Max Activating Token Index: 420

Text #17

Max Range: 3.0255. Min Range: -3.0255

Max Act: 2.7316. Min Act: -0.1700

Data Index: 2477974 (Open Web Text)

Max Activating Token Index: 196

Text #18

Max Range: 3.0255. Min Range: -3.0255

Max Act: 2.7226. Min Act: -0.1700

Data Index: 838689 (Open Web Text)

Max Activating Token Index: 540

Text #19

Max Range: 3.0255. Min Range: -3.0255

Max Act: 2.7150. Min Act: -0.1700

Data Index: 3531062 (Open Web Text)

Max Activating Token Index: 92