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

Dataset: Open Web Text

Neuron 3028 in Layer 6

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: 3.7545. Min Range: -3.7545

Max Act: 3.7477. Min Act: -0.1700

Data Index: 1442460 (Open Web Text)

Max Activating Token Index: 851

Text #1

Max Range: 3.7545. Min Range: -3.7545

Max Act: 3.7545. Min Act: -0.1700

Data Index: 1394557 (Open Web Text)

Max Activating Token Index: 103

Text #2

Max Range: 3.7545. Min Range: -3.7545

Max Act: 3.7226. Min Act: -0.1700

Data Index: 8661324 (Open Web Text)

Max Activating Token Index: 947

Text #3

Max Range: 3.7545. Min Range: -3.7545

Max Act: 3.7384. Min Act: -0.1700

Data Index: 7453217 (Open Web Text)

Max Activating Token Index: 35

Text #4

Max Range: 3.7545. Min Range: -3.7545

Max Act: 3.7208. Min Act: -0.1700

Data Index: 5558418 (Open Web Text)

Max Activating Token Index: 552

Text #5

Max Range: 3.7545. Min Range: -3.7545

Max Act: 3.7299. Min Act: -0.1700

Data Index: 5102809 (Open Web Text)

Max Activating Token Index: 46

Text #6

Max Range: 3.7545. Min Range: -3.7545

Max Act: 3.7390. Min Act: -0.1700

Data Index: 1576030 (Open Web Text)

Max Activating Token Index: 73

Text #7

Max Range: 3.7545. Min Range: -3.7545

Max Act: 3.7058. Min Act: -0.1700

Data Index: 5977321 (Open Web Text)

Max Activating Token Index: 609

Text #8

Max Range: 3.7545. Min Range: -3.7545

Max Act: 3.6834. Min Act: -0.1700

Data Index: 2423343 (Open Web Text)

Max Activating Token Index: 494

Text #9

Max Range: 3.7545. Min Range: -3.7545

Max Act: 3.7043. Min Act: -0.1700

Data Index: 3739252 (Open Web Text)

Max Activating Token Index: 515

Text #10

Max Range: 3.7545. Min Range: -3.7545

Max Act: 3.6881. Min Act: -0.1700

Data Index: 493050 (Open Web Text)

Max Activating Token Index: 69

Text #11

Max Range: 3.7545. Min Range: -3.7545

Max Act: 3.6995. Min Act: -0.1700

Data Index: 6922649 (Open Web Text)

Max Activating Token Index: 151

Text #12

Max Range: 3.7545. Min Range: -3.7545

Max Act: 3.7074. Min Act: -0.1700

Data Index: 4592625 (Open Web Text)

Max Activating Token Index: 811

Text #13

Max Range: 3.7545. Min Range: -3.7545

Max Act: 3.6814. Min Act: -0.1700

Data Index: 5004926 (Open Web Text)

Max Activating Token Index: 512

Text #14

Max Range: 3.7545. Min Range: -3.7545

Max Act: 3.6659. Min Act: -0.1700

Data Index: 3135652 (Open Web Text)

Max Activating Token Index: 447

Text #15

Max Range: 3.7545. Min Range: -3.7545

Max Act: 3.6715. Min Act: -0.1700

Data Index: 919528 (Open Web Text)

Max Activating Token Index: 146

Text #16

Max Range: 3.7545. Min Range: -3.7545

Max Act: 3.6703. Min Act: -0.1700

Data Index: 1901481 (Open Web Text)

Max Activating Token Index: 485

Text #17

Max Range: 3.7545. Min Range: -3.7545

Max Act: 3.6521. Min Act: -0.1700

Data Index: 4475247 (Open Web Text)

Max Activating Token Index: 875

Text #18

Max Range: 3.7545. Min Range: -3.7545

Max Act: 3.6723. Min Act: -0.1700

Data Index: 6240372 (Open Web Text)

Max Activating Token Index: 88

Text #19

Max Range: 3.7545. Min Range: -3.7545

Max Act: 3.6673. Min Act: -0.1700

Data Index: 3124211 (Open Web Text)

Max Activating Token Index: 636