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

Dataset: Open Web Text

Neuron 717 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: 1.5286. Min Range: -1.5286

Max Act: 1.5224. Min Act: -0.1700

Data Index: 3048729 (Open Web Text)

Max Activating Token Index: 198

Text #1

Max Range: 1.5286. Min Range: -1.5286

Max Act: 1.5286. Min Act: -0.1700

Data Index: 6154751 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 1.5286. Min Range: -1.5286

Max Act: 1.5078. Min Act: -0.1700

Data Index: 3071887 (Open Web Text)

Max Activating Token Index: 604

Text #3

Max Range: 1.5286. Min Range: -1.5286

Max Act: 1.5046. Min Act: -0.1700

Data Index: 644884 (Open Web Text)

Max Activating Token Index: 177

Text #4

Max Range: 1.5286. Min Range: -1.5286

Max Act: 1.4929. Min Act: -0.1700

Data Index: 3713447 (Open Web Text)

Max Activating Token Index: 12

Text #5

Max Range: 1.5286. Min Range: -1.5286

Max Act: 1.4886. Min Act: -0.1700

Data Index: 6918445 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 1.5286. Min Range: -1.5286

Max Act: 1.4886. Min Act: -0.1700

Data Index: 1562228 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 1.5286. Min Range: -1.5286

Max Act: 1.4886. Min Act: -0.1700

Data Index: 7639521 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 1.5286. Min Range: -1.5286

Max Act: 1.4936. Min Act: -0.1700

Data Index: 3101841 (Open Web Text)

Max Activating Token Index: 52

Text #9

Max Range: 1.5286. Min Range: -1.5286

Max Act: 1.4908. Min Act: -0.1700

Data Index: 316726 (Open Web Text)

Max Activating Token Index: 175

Text #10

Max Range: 1.5286. Min Range: -1.5286

Max Act: 1.4791. Min Act: -0.1700

Data Index: 7109391 (Open Web Text)

Max Activating Token Index: 29

Text #11

Max Range: 1.5286. Min Range: -1.5286

Max Act: 1.4758. Min Act: -0.1700

Data Index: 7133162 (Open Web Text)

Max Activating Token Index: 16

Text #12

Max Range: 1.5286. Min Range: -1.5286

Max Act: 1.4636. Min Act: -0.1700

Data Index: 3250585 (Open Web Text)

Max Activating Token Index: 453

Text #13

Max Range: 1.5286. Min Range: -1.5286

Max Act: 1.4686. Min Act: -0.1700

Data Index: 4143781 (Open Web Text)

Max Activating Token Index: 918

Text #14

Max Range: 1.5286. Min Range: -1.5286

Max Act: 1.4791. Min Act: -0.1700

Data Index: 6019581 (Open Web Text)

Max Activating Token Index: 288

Text #15

Max Range: 1.5286. Min Range: -1.5286

Max Act: 1.4607. Min Act: -0.1700

Data Index: 4250875 (Open Web Text)

Max Activating Token Index: 201

Text #16

Max Range: 1.5286. Min Range: -1.5286

Max Act: 1.4659. Min Act: -0.1700

Data Index: 8399194 (Open Web Text)

Max Activating Token Index: 20

Text #17

Max Range: 1.5286. Min Range: -1.5286

Max Act: 1.4688. Min Act: -0.1699

Data Index: 8516575 (Open Web Text)

Max Activating Token Index: 182

Text #18

Max Range: 1.5286. Min Range: -1.5286

Max Act: 1.4744. Min Act: -0.1700

Data Index: 2234610 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 1.5286. Min Range: -1.5286

Max Act: 1.4712. Min Act: -0.1695

Data Index: 5984746 (Open Web Text)

Max Activating Token Index: 561