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

Dataset: Open Web Text

Neuron 2624 in Layer 0

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: 6.6566. Min Range: -6.6566

Max Act: 6.6566. Min Act: -0.1700

Data Index: 830142 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 6.6566. Min Range: -6.6566

Max Act: 6.6450. Min Act: -0.1700

Data Index: 938884 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 6.6566. Min Range: -6.6566

Max Act: 6.5643. Min Act: -0.1700

Data Index: 233511 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 6.6566. Min Range: -6.6566

Max Act: 6.5831. Min Act: -0.1700

Data Index: 8025539 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 6.6566. Min Range: -6.6566

Max Act: 6.5615. Min Act: -0.1700

Data Index: 7900227 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 6.6566. Min Range: -6.6566

Max Act: 6.5694. Min Act: -0.1700

Data Index: 1329635 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 6.6566. Min Range: -6.6566

Max Act: 6.5970. Min Act: -0.1700

Data Index: 2863027 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 6.6566. Min Range: -6.6566

Max Act: 6.5112. Min Act: -0.1700

Data Index: 1420624 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 6.6566. Min Range: -6.6566

Max Act: 6.4932. Min Act: -0.1700

Data Index: 5847555 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 6.6566. Min Range: -6.6566

Max Act: 6.5380. Min Act: -0.1700

Data Index: 5741333 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 6.6566. Min Range: -6.6566

Max Act: 6.5364. Min Act: -0.1700

Data Index: 4548834 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 6.6566. Min Range: -6.6566

Max Act: 6.5208. Min Act: -0.1700

Data Index: 3966753 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 6.6566. Min Range: -6.6566

Max Act: 6.5380. Min Act: -0.1700

Data Index: 3891228 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 6.6566. Min Range: -6.6566

Max Act: 6.5148. Min Act: -0.1700

Data Index: 3846550 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 6.6566. Min Range: -6.6566

Max Act: 6.5079. Min Act: -0.1700

Data Index: 41698 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 6.6566. Min Range: -6.6566

Max Act: 6.5352. Min Act: -0.1700

Data Index: 998390 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 6.6566. Min Range: -6.6566

Max Act: 6.5214. Min Act: -0.1699

Data Index: 3293569 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 6.6566. Min Range: -6.6566

Max Act: 6.5197. Min Act: -0.1700

Data Index: 871753 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 6.6566. Min Range: -6.6566

Max Act: 6.5131. Min Act: -0.1700

Data Index: 2680600 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 6.6566. Min Range: -6.6566

Max Act: 6.5265. Min Act: -0.1700

Data Index: 2572846 (Open Web Text)

Max Activating Token Index: 4