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

Dataset: Open Web Text

Neuron 2096 in Layer 3

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: 3.5276. Min Range: -3.5276

Max Act: 3.5276. Min Act: -0.1700

Data Index: 8636976 (Open Web Text)

Max Activating Token Index: 743

Text #1

Max Range: 3.5276. Min Range: -3.5276

Max Act: 3.4706. Min Act: -0.1700

Data Index: 4669035 (Open Web Text)

Max Activating Token Index: 1000

Text #2

Max Range: 3.5276. Min Range: -3.5276

Max Act: 3.4284. Min Act: -0.1700

Data Index: 3123255 (Open Web Text)

Max Activating Token Index: 1019

Text #3

Max Range: 3.5276. Min Range: -3.5276

Max Act: 3.4546. Min Act: -0.1700

Data Index: 7694409 (Open Web Text)

Max Activating Token Index: 393

Text #4

Max Range: 3.5276. Min Range: -3.5276

Max Act: 3.4474. Min Act: -0.1700

Data Index: 7403015 (Open Web Text)

Max Activating Token Index: 151

Text #5

Max Range: 3.5276. Min Range: -3.5276

Max Act: 3.4395. Min Act: -0.1700

Data Index: 539579 (Open Web Text)

Max Activating Token Index: 654

Text #6

Max Range: 3.5276. Min Range: -3.5276

Max Act: 3.4262. Min Act: -0.1700

Data Index: 7833251 (Open Web Text)

Max Activating Token Index: 644

Text #7

Max Range: 3.5276. Min Range: -3.5276

Max Act: 3.4366. Min Act: -0.1700

Data Index: 42663 (Open Web Text)

Max Activating Token Index: 997

Text #8

Max Range: 3.5276. Min Range: -3.5276

Max Act: 3.4134. Min Act: -0.1700

Data Index: 3436737 (Open Web Text)

Max Activating Token Index: 118

Text #9

Max Range: 3.5276. Min Range: -3.5276

Max Act: 3.3989. Min Act: -0.1700

Data Index: 176565 (Open Web Text)

Max Activating Token Index: 919

Text #10

Max Range: 3.5276. Min Range: -3.5276

Max Act: 3.3899. Min Act: -0.1700

Data Index: 3128943 (Open Web Text)

Max Activating Token Index: 990

Text #11

Max Range: 3.5276. Min Range: -3.5276

Max Act: 3.4044. Min Act: -0.1700

Data Index: 1515297 (Open Web Text)

Max Activating Token Index: 902

Text #12

Max Range: 3.5276. Min Range: -3.5276

Max Act: 3.3889. Min Act: -0.1700

Data Index: 5964499 (Open Web Text)

Max Activating Token Index: 975

Text #13

Max Range: 3.5276. Min Range: -3.5276

Max Act: 3.3959. Min Act: -0.1700

Data Index: 3617257 (Open Web Text)

Max Activating Token Index: 320

Text #14

Max Range: 3.5276. Min Range: -3.5276

Max Act: 3.3869. Min Act: -0.1700

Data Index: 6424583 (Open Web Text)

Max Activating Token Index: 885

Text #15

Max Range: 3.5276. Min Range: -3.5276

Max Act: 3.3892. Min Act: -0.1700

Data Index: 7318059 (Open Web Text)

Max Activating Token Index: 655

Text #16

Max Range: 3.5276. Min Range: -3.5276

Max Act: 3.3983. Min Act: -0.1700

Data Index: 2024878 (Open Web Text)

Max Activating Token Index: 991

Text #17

Max Range: 3.5276. Min Range: -3.5276

Max Act: 3.3754. Min Act: -0.1700

Data Index: 3662589 (Open Web Text)

Max Activating Token Index: 974

Text #18

Max Range: 3.5276. Min Range: -3.5276

Max Act: 3.3911. Min Act: -0.1700

Data Index: 3353528 (Open Web Text)

Max Activating Token Index: 392

Text #19

Max Range: 3.5276. Min Range: -3.5276

Max Act: 3.4001. Min Act: -0.1700

Data Index: 5310222 (Open Web Text)

Max Activating Token Index: 65