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

Dataset: Open Web Text

Neuron 2374 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: 4.2525. Min Range: -4.2525

Max Act: 4.2525. Min Act: -0.1700

Data Index: 6035758 (Open Web Text)

Max Activating Token Index: 517

Text #1

Max Range: 4.2525. Min Range: -4.2525

Max Act: 4.1945. Min Act: -0.1700

Data Index: 1998977 (Open Web Text)

Max Activating Token Index: 455

Text #2

Max Range: 4.2525. Min Range: -4.2525

Max Act: 4.1301. Min Act: -0.1700

Data Index: 72705 (Open Web Text)

Max Activating Token Index: 684

Text #3

Max Range: 4.2525. Min Range: -4.2525

Max Act: 4.1224. Min Act: -0.1700

Data Index: 919338 (Open Web Text)

Max Activating Token Index: 508

Text #4

Max Range: 4.2525. Min Range: -4.2525

Max Act: 4.0691. Min Act: -0.1700

Data Index: 7097902 (Open Web Text)

Max Activating Token Index: 170

Text #5

Max Range: 4.2525. Min Range: -4.2525

Max Act: 4.0673. Min Act: -0.1700

Data Index: 3356749 (Open Web Text)

Max Activating Token Index: 624

Text #6

Max Range: 4.2525. Min Range: -4.2525

Max Act: 4.0633. Min Act: -0.1700

Data Index: 4623943 (Open Web Text)

Max Activating Token Index: 702

Text #7

Max Range: 4.2525. Min Range: -4.2525

Max Act: 4.0348. Min Act: -0.1700

Data Index: 3630988 (Open Web Text)

Max Activating Token Index: 312

Text #8

Max Range: 4.2525. Min Range: -4.2525

Max Act: 4.0496. Min Act: -0.1700

Data Index: 3443152 (Open Web Text)

Max Activating Token Index: 477

Text #9

Max Range: 4.2525. Min Range: -4.2525

Max Act: 4.0607. Min Act: -0.1700

Data Index: 3383980 (Open Web Text)

Max Activating Token Index: 473

Text #10

Max Range: 4.2525. Min Range: -4.2525

Max Act: 4.0482. Min Act: -0.1700

Data Index: 8738563 (Open Web Text)

Max Activating Token Index: 70

Text #11

Max Range: 4.2525. Min Range: -4.2525

Max Act: 4.0722. Min Act: -0.1700

Data Index: 5418981 (Open Web Text)

Max Activating Token Index: 375

Text #12

Max Range: 4.2525. Min Range: -4.2525

Max Act: 4.0474. Min Act: -0.1700

Data Index: 4767623 (Open Web Text)

Max Activating Token Index: 944

Text #13

Max Range: 4.2525. Min Range: -4.2525

Max Act: 4.0510. Min Act: -0.1700

Data Index: 4488426 (Open Web Text)

Max Activating Token Index: 575

Text #14

Max Range: 4.2525. Min Range: -4.2525

Max Act: 4.0119. Min Act: -0.1700

Data Index: 6249944 (Open Web Text)

Max Activating Token Index: 541

Text #15

Max Range: 4.2525. Min Range: -4.2525

Max Act: 4.0408. Min Act: -0.1700

Data Index: 6428237 (Open Web Text)

Max Activating Token Index: 226

Text #16

Max Range: 4.2525. Min Range: -4.2525

Max Act: 4.0255. Min Act: -0.1700

Data Index: 1499832 (Open Web Text)

Max Activating Token Index: 529

Text #17

Max Range: 4.2525. Min Range: -4.2525

Max Act: 4.0234. Min Act: -0.1700

Data Index: 5421149 (Open Web Text)

Max Activating Token Index: 386

Text #18

Max Range: 4.2525. Min Range: -4.2525

Max Act: 4.0271. Min Act: -0.1700

Data Index: 223663 (Open Web Text)

Max Activating Token Index: 767

Text #19

Max Range: 4.2525. Min Range: -4.2525

Max Act: 4.0347. Min Act: -0.1700

Data Index: 1010337 (Open Web Text)

Max Activating Token Index: 261