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

Dataset: Open Web Text

Neuron 1310 in Layer 5

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: 4.6949. Min Range: -4.6949

Max Act: 4.6949. Min Act: -0.1700

Data Index: 2497852 (Open Web Text)

Max Activating Token Index: 95

Text #1

Max Range: 4.6949. Min Range: -4.6949

Max Act: 4.6240. Min Act: -0.1700

Data Index: 5736208 (Open Web Text)

Max Activating Token Index: 261

Text #2

Max Range: 4.6949. Min Range: -4.6949

Max Act: 4.5974. Min Act: -0.1700

Data Index: 1081172 (Open Web Text)

Max Activating Token Index: 475

Text #3

Max Range: 4.6949. Min Range: -4.6949

Max Act: 4.5930. Min Act: -0.1700

Data Index: 2871068 (Open Web Text)

Max Activating Token Index: 36

Text #4

Max Range: 4.6949. Min Range: -4.6949

Max Act: 4.6015. Min Act: -0.1700

Data Index: 1998998 (Open Web Text)

Max Activating Token Index: 701

Text #5

Max Range: 4.6949. Min Range: -4.6949

Max Act: 4.5875. Min Act: -0.1700

Data Index: 1551356 (Open Web Text)

Max Activating Token Index: 90

Text #6

Max Range: 4.6949. Min Range: -4.6949

Max Act: 4.5768. Min Act: -0.1700

Data Index: 1242645 (Open Web Text)

Max Activating Token Index: 62

Text #7

Max Range: 4.6949. Min Range: -4.6949

Max Act: 4.5793. Min Act: -0.1700

Data Index: 1751367 (Open Web Text)

Max Activating Token Index: 294

Text #8

Max Range: 4.6949. Min Range: -4.6949

Max Act: 4.5573. Min Act: -0.1700

Data Index: 2106854 (Open Web Text)

Max Activating Token Index: 614

Text #9

Max Range: 4.6949. Min Range: -4.6949

Max Act: 4.5197. Min Act: -0.1700

Data Index: 2908707 (Open Web Text)

Max Activating Token Index: 327

Text #10

Max Range: 4.6949. Min Range: -4.6949

Max Act: 4.5555. Min Act: -0.1700

Data Index: 521955 (Open Web Text)

Max Activating Token Index: 517

Text #11

Max Range: 4.6949. Min Range: -4.6949

Max Act: 4.5269. Min Act: -0.1700

Data Index: 8447439 (Open Web Text)

Max Activating Token Index: 644

Text #12

Max Range: 4.6949. Min Range: -4.6949

Max Act: 4.5368. Min Act: -0.1700

Data Index: 8150834 (Open Web Text)

Max Activating Token Index: 622

Text #13

Max Range: 4.6949. Min Range: -4.6949

Max Act: 4.5251. Min Act: -0.1700

Data Index: 2122866 (Open Web Text)

Max Activating Token Index: 93

Text #14

Max Range: 4.6949. Min Range: -4.6949

Max Act: 4.5230. Min Act: -0.1700

Data Index: 7204360 (Open Web Text)

Max Activating Token Index: 72

Text #15

Max Range: 4.6949. Min Range: -4.6949

Max Act: 4.5379. Min Act: -0.1700

Data Index: 4262388 (Open Web Text)

Max Activating Token Index: 150

Text #16

Max Range: 4.6949. Min Range: -4.6949

Max Act: 4.5203. Min Act: -0.1700

Data Index: 1128637 (Open Web Text)

Max Activating Token Index: 753

Text #17

Max Range: 4.6949. Min Range: -4.6949

Max Act: 4.5196. Min Act: -0.1700

Data Index: 1190231 (Open Web Text)

Max Activating Token Index: 249

Text #18

Max Range: 4.6949. Min Range: -4.6949

Max Act: 4.5328. Min Act: -0.1700

Data Index: 3089238 (Open Web Text)

Max Activating Token Index: 1022

Text #19

Max Range: 4.6949. Min Range: -4.6949

Max Act: 4.4981. Min Act: -0.1700

Data Index: 5305011 (Open Web Text)

Max Activating Token Index: 491