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

Dataset: Open Web Text

Neuron 1831 in Layer 4

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: 4.5360. Min Range: -4.5360

Max Act: 4.5360. Min Act: -0.1700

Data Index: 4124892 (Open Web Text)

Max Activating Token Index: 944

Text #1

Max Range: 4.5360. Min Range: -4.5360

Max Act: 4.4779. Min Act: -0.1700

Data Index: 7630482 (Open Web Text)

Max Activating Token Index: 215

Text #2

Max Range: 4.5360. Min Range: -4.5360

Max Act: 4.5025. Min Act: -0.1700

Data Index: 6173346 (Open Web Text)

Max Activating Token Index: 691

Text #3

Max Range: 4.5360. Min Range: -4.5360

Max Act: 4.4747. Min Act: -0.1700

Data Index: 4610667 (Open Web Text)

Max Activating Token Index: 310

Text #4

Max Range: 4.5360. Min Range: -4.5360

Max Act: 4.5045. Min Act: -0.1700

Data Index: 1629424 (Open Web Text)

Max Activating Token Index: 462

Text #5

Max Range: 4.5360. Min Range: -4.5360

Max Act: 4.4708. Min Act: -0.1700

Data Index: 595018 (Open Web Text)

Max Activating Token Index: 242

Text #6

Max Range: 4.5360. Min Range: -4.5360

Max Act: 4.4802. Min Act: -0.1700

Data Index: 842022 (Open Web Text)

Max Activating Token Index: 471

Text #7

Max Range: 4.5360. Min Range: -4.5360

Max Act: 4.4656. Min Act: -0.1700

Data Index: 1356055 (Open Web Text)

Max Activating Token Index: 667

Text #8

Max Range: 4.5360. Min Range: -4.5360

Max Act: 4.4764. Min Act: -0.1700

Data Index: 4483105 (Open Web Text)

Max Activating Token Index: 72

Text #9

Max Range: 4.5360. Min Range: -4.5360

Max Act: 4.4617. Min Act: -0.1700

Data Index: 4157902 (Open Web Text)

Max Activating Token Index: 364

Text #10

Max Range: 4.5360. Min Range: -4.5360

Max Act: 4.4638. Min Act: -0.1700

Data Index: 2995554 (Open Web Text)

Max Activating Token Index: 315

Text #11

Max Range: 4.5360. Min Range: -4.5360

Max Act: 4.4500. Min Act: -0.1700

Data Index: 2296384 (Open Web Text)

Max Activating Token Index: 315

Text #12

Max Range: 4.5360. Min Range: -4.5360

Max Act: 4.4267. Min Act: -0.1700

Data Index: 7019987 (Open Web Text)

Max Activating Token Index: 364

Text #13

Max Range: 4.5360. Min Range: -4.5360

Max Act: 4.4407. Min Act: -0.1700

Data Index: 8656476 (Open Web Text)

Max Activating Token Index: 760

Text #14

Max Range: 4.5360. Min Range: -4.5360

Max Act: 4.4461. Min Act: -0.1700

Data Index: 3877827 (Open Web Text)

Max Activating Token Index: 691

Text #15

Max Range: 4.5360. Min Range: -4.5360

Max Act: 4.4128. Min Act: -0.1700

Data Index: 7255569 (Open Web Text)

Max Activating Token Index: 112

Text #16

Max Range: 4.5360. Min Range: -4.5360

Max Act: 4.4407. Min Act: -0.1700

Data Index: 1766377 (Open Web Text)

Max Activating Token Index: 451

Text #17

Max Range: 4.5360. Min Range: -4.5360

Max Act: 4.4431. Min Act: -0.1700

Data Index: 869770 (Open Web Text)

Max Activating Token Index: 1009

Text #18

Max Range: 4.5360. Min Range: -4.5360

Max Act: 4.4128. Min Act: -0.1700

Data Index: 8259673 (Open Web Text)

Max Activating Token Index: 669

Text #19

Max Range: 4.5360. Min Range: -4.5360

Max Act: 4.4197. Min Act: -0.1700

Data Index: 1177858 (Open Web Text)

Max Activating Token Index: 93