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

Dataset: Open Web Text

Neuron 2025 in Layer 2

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: 5.0892. Min Range: -5.0892

Max Act: 5.0892. Min Act: -0.1700

Data Index: 7498530 (Open Web Text)

Max Activating Token Index: 886

Text #1

Max Range: 5.0892. Min Range: -5.0892

Max Act: 5.0529. Min Act: -0.1700

Data Index: 3332113 (Open Web Text)

Max Activating Token Index: 286

Text #2

Max Range: 5.0892. Min Range: -5.0892

Max Act: 4.9603. Min Act: -0.1700

Data Index: 8423248 (Open Web Text)

Max Activating Token Index: 454

Text #3

Max Range: 5.0892. Min Range: -5.0892

Max Act: 4.9094. Min Act: -0.1700

Data Index: 4767580 (Open Web Text)

Max Activating Token Index: 838

Text #4

Max Range: 5.0892. Min Range: -5.0892

Max Act: 4.8785. Min Act: -0.1700

Data Index: 2846235 (Open Web Text)

Max Activating Token Index: 927

Text #5

Max Range: 5.0892. Min Range: -5.0892

Max Act: 4.8340. Min Act: -0.1700

Data Index: 5113928 (Open Web Text)

Max Activating Token Index: 798

Text #6

Max Range: 5.0892. Min Range: -5.0892

Max Act: 4.9110. Min Act: -0.1700

Data Index: 5479221 (Open Web Text)

Max Activating Token Index: 1008

Text #7

Max Range: 5.0892. Min Range: -5.0892

Max Act: 4.8595. Min Act: -0.1700

Data Index: 2636893 (Open Web Text)

Max Activating Token Index: 147

Text #8

Max Range: 5.0892. Min Range: -5.0892

Max Act: 4.8580. Min Act: -0.1700

Data Index: 6188211 (Open Web Text)

Max Activating Token Index: 395

Text #9

Max Range: 5.0892. Min Range: -5.0892

Max Act: 4.8451. Min Act: -0.1700

Data Index: 5765444 (Open Web Text)

Max Activating Token Index: 688

Text #10

Max Range: 5.0892. Min Range: -5.0892

Max Act: 4.8658. Min Act: -0.1700

Data Index: 1376742 (Open Web Text)

Max Activating Token Index: 27

Text #11

Max Range: 5.0892. Min Range: -5.0892

Max Act: 4.8249. Min Act: -0.1700

Data Index: 3119104 (Open Web Text)

Max Activating Token Index: 205

Text #12

Max Range: 5.0892. Min Range: -5.0892

Max Act: 4.7926. Min Act: -0.1700

Data Index: 1293545 (Open Web Text)

Max Activating Token Index: 75

Text #13

Max Range: 5.0892. Min Range: -5.0892

Max Act: 4.7279. Min Act: -0.1700

Data Index: 2714703 (Open Web Text)

Max Activating Token Index: 834

Text #14

Max Range: 5.0892. Min Range: -5.0892

Max Act: 4.7663. Min Act: -0.1700

Data Index: 3640857 (Open Web Text)

Max Activating Token Index: 1005

Text #15

Max Range: 5.0892. Min Range: -5.0892

Max Act: 4.7461. Min Act: -0.1700

Data Index: 535567 (Open Web Text)

Max Activating Token Index: 123

Text #16

Max Range: 5.0892. Min Range: -5.0892

Max Act: 4.7561. Min Act: -0.1700

Data Index: 2815900 (Open Web Text)

Max Activating Token Index: 52

Text #17

Max Range: 5.0892. Min Range: -5.0892

Max Act: 4.7694. Min Act: -0.1700

Data Index: 6566605 (Open Web Text)

Max Activating Token Index: 815

Text #18

Max Range: 5.0892. Min Range: -5.0892

Max Act: 4.7783. Min Act: -0.1700

Data Index: 6965486 (Open Web Text)

Max Activating Token Index: 912

Text #19

Max Range: 5.0892. Min Range: -5.0892

Max Act: 4.7752. Min Act: -0.1700

Data Index: 3535625 (Open Web Text)

Max Activating Token Index: 240