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

Dataset: Open Web Text

Neuron 692 in Layer 1

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: 1.4896. Min Range: -1.4896

Max Act: 1.4896. Min Act: -0.1700

Data Index: 2641998 (Open Web Text)

Max Activating Token Index: 11

Text #1

Max Range: 1.4896. Min Range: -1.4896

Max Act: 1.4867. Min Act: -0.1700

Data Index: 1786554 (Open Web Text)

Max Activating Token Index: 400

Text #2

Max Range: 1.4896. Min Range: -1.4896

Max Act: 1.4885. Min Act: -0.1700

Data Index: 3070262 (Open Web Text)

Max Activating Token Index: 928

Text #3

Max Range: 1.4896. Min Range: -1.4896

Max Act: 1.4824. Min Act: -0.1700

Data Index: 1614290 (Open Web Text)

Max Activating Token Index: 1006

Text #4

Max Range: 1.4896. Min Range: -1.4896

Max Act: 1.4728. Min Act: -0.1700

Data Index: 1341039 (Open Web Text)

Max Activating Token Index: 1007

Text #5

Max Range: 1.4896. Min Range: -1.4896

Max Act: 1.4837. Min Act: -0.1700

Data Index: 5125204 (Open Web Text)

Max Activating Token Index: 307

Text #6

Max Range: 1.4896. Min Range: -1.4896

Max Act: 1.4812. Min Act: -0.1700

Data Index: 2317420 (Open Web Text)

Max Activating Token Index: 981

Text #7

Max Range: 1.4896. Min Range: -1.4896

Max Act: 1.4650. Min Act: -0.1700

Data Index: 8402319 (Open Web Text)

Max Activating Token Index: 692

Text #8

Max Range: 1.4896. Min Range: -1.4896

Max Act: 1.4738. Min Act: -0.1700

Data Index: 3747176 (Open Web Text)

Max Activating Token Index: 998

Text #9

Max Range: 1.4896. Min Range: -1.4896

Max Act: 1.4703. Min Act: -0.1700

Data Index: 1847550 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 1.4896. Min Range: -1.4896

Max Act: 1.4675. Min Act: -0.1700

Data Index: 7127629 (Open Web Text)

Max Activating Token Index: 447

Text #11

Max Range: 1.4896. Min Range: -1.4896

Max Act: 1.4590. Min Act: -0.1700

Data Index: 1189159 (Open Web Text)

Max Activating Token Index: 255

Text #12

Max Range: 1.4896. Min Range: -1.4896

Max Act: 1.4570. Min Act: -0.1700

Data Index: 1399567 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 1.4896. Min Range: -1.4896

Max Act: 1.4503. Min Act: -0.1700

Data Index: 4447642 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 1.4896. Min Range: -1.4896

Max Act: 1.4605. Min Act: -0.1700

Data Index: 4515187 (Open Web Text)

Max Activating Token Index: 10

Text #15

Max Range: 1.4896. Min Range: -1.4896

Max Act: 1.4569. Min Act: -0.1700

Data Index: 8320643 (Open Web Text)

Max Activating Token Index: 178

Text #16

Max Range: 1.4896. Min Range: -1.4896

Max Act: 1.4428. Min Act: -0.1700

Data Index: 4352298 (Open Web Text)

Max Activating Token Index: 532

Text #17

Max Range: 1.4896. Min Range: -1.4896

Max Act: 1.4442. Min Act: -0.1700

Data Index: 1366644 (Open Web Text)

Max Activating Token Index: 347

Text #18

Max Range: 1.4896. Min Range: -1.4896

Max Act: 1.4358. Min Act: -0.1700

Data Index: 2008326 (Open Web Text)

Max Activating Token Index: 240

Text #19

Max Range: 1.4896. Min Range: -1.4896

Max Act: 1.4440. Min Act: -0.1700

Data Index: 548377 (Open Web Text)

Max Activating Token Index: 990