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

Dataset: Open Web Text

Neuron 92 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: 3.4093. Min Range: -3.4093

Max Act: 3.4093. Min Act: -0.1700

Data Index: 2976959 (Open Web Text)

Max Activating Token Index: 320

Text #1

Max Range: 3.4093. Min Range: -3.4093

Max Act: 3.3434. Min Act: -0.1700

Data Index: 3297170 (Open Web Text)

Max Activating Token Index: 857

Text #2

Max Range: 3.4093. Min Range: -3.4093

Max Act: 3.2900. Min Act: -0.1700

Data Index: 67577 (Open Web Text)

Max Activating Token Index: 785

Text #3

Max Range: 3.4093. Min Range: -3.4093

Max Act: 3.1976. Min Act: -0.1700

Data Index: 2666531 (Open Web Text)

Max Activating Token Index: 83

Text #4

Max Range: 3.4093. Min Range: -3.4093

Max Act: 3.1805. Min Act: -0.1700

Data Index: 8665101 (Open Web Text)

Max Activating Token Index: 701

Text #5

Max Range: 3.4093. Min Range: -3.4093

Max Act: 3.2123. Min Act: -0.1700

Data Index: 6639921 (Open Web Text)

Max Activating Token Index: 372

Text #6

Max Range: 3.4093. Min Range: -3.4093

Max Act: 3.1923. Min Act: -0.1700

Data Index: 7033473 (Open Web Text)

Max Activating Token Index: 528

Text #7

Max Range: 3.4093. Min Range: -3.4093

Max Act: 3.1348. Min Act: -0.1700

Data Index: 2804549 (Open Web Text)

Max Activating Token Index: 1011

Text #8

Max Range: 3.4093. Min Range: -3.4093

Max Act: 3.1416. Min Act: -0.1700

Data Index: 2758085 (Open Web Text)

Max Activating Token Index: 54

Text #9

Max Range: 3.4093. Min Range: -3.4093

Max Act: 3.1433. Min Act: -0.1700

Data Index: 873208 (Open Web Text)

Max Activating Token Index: 722

Text #10

Max Range: 3.4093. Min Range: -3.4093

Max Act: 3.1300. Min Act: -0.1700

Data Index: 7713595 (Open Web Text)

Max Activating Token Index: 248

Text #11

Max Range: 3.4093. Min Range: -3.4093

Max Act: 3.1232. Min Act: -0.1700

Data Index: 240114 (Open Web Text)

Max Activating Token Index: 367

Text #12

Max Range: 3.4093. Min Range: -3.4093

Max Act: 3.1319. Min Act: -0.1700

Data Index: 6199100 (Open Web Text)

Max Activating Token Index: 518

Text #13

Max Range: 3.4093. Min Range: -3.4093

Max Act: 3.0992. Min Act: -0.1700

Data Index: 5743567 (Open Web Text)

Max Activating Token Index: 438

Text #14

Max Range: 3.4093. Min Range: -3.4093

Max Act: 3.1191. Min Act: -0.1700

Data Index: 164688 (Open Web Text)

Max Activating Token Index: 819

Text #15

Max Range: 3.4093. Min Range: -3.4093

Max Act: 3.0971. Min Act: -0.1700

Data Index: 4566050 (Open Web Text)

Max Activating Token Index: 770

Text #16

Max Range: 3.4093. Min Range: -3.4093

Max Act: 3.0574. Min Act: -0.1700

Data Index: 5438278 (Open Web Text)

Max Activating Token Index: 891

Text #17

Max Range: 3.4093. Min Range: -3.4093

Max Act: 3.0590. Min Act: -0.1700

Data Index: 8082297 (Open Web Text)

Max Activating Token Index: 960

Text #18

Max Range: 3.4093. Min Range: -3.4093

Max Act: 3.0760. Min Act: -0.1700

Data Index: 1808347 (Open Web Text)

Max Activating Token Index: 726

Text #19

Max Range: 3.4093. Min Range: -3.4093

Max Act: 3.0760. Min Act: -0.1700

Data Index: 245529 (Open Web Text)

Max Activating Token Index: 291