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

Dataset: Open Web Text

Neuron 1110 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: 1.9246. Min Range: -1.9246

Max Act: 1.9162. Min Act: -0.1700

Data Index: 3195454 (Open Web Text)

Max Activating Token Index: 331

Text #1

Max Range: 1.9246. Min Range: -1.9246

Max Act: 1.9246. Min Act: -0.1700

Data Index: 3256103 (Open Web Text)

Max Activating Token Index: 777

Text #2

Max Range: 1.9246. Min Range: -1.9246

Max Act: 1.8801. Min Act: -0.1700

Data Index: 4227999 (Open Web Text)

Max Activating Token Index: 131

Text #3

Max Range: 1.9246. Min Range: -1.9246

Max Act: 1.8985. Min Act: -0.1700

Data Index: 3545184 (Open Web Text)

Max Activating Token Index: 223

Text #4

Max Range: 1.9246. Min Range: -1.9246

Max Act: 1.8647. Min Act: -0.1700

Data Index: 3176870 (Open Web Text)

Max Activating Token Index: 374

Text #5

Max Range: 1.9246. Min Range: -1.9246

Max Act: 1.8601. Min Act: -0.1700

Data Index: 6511329 (Open Web Text)

Max Activating Token Index: 403

Text #6

Max Range: 1.9246. Min Range: -1.9246

Max Act: 1.8705. Min Act: -0.1700

Data Index: 378482 (Open Web Text)

Max Activating Token Index: 303

Text #7

Max Range: 1.9246. Min Range: -1.9246

Max Act: 1.8717. Min Act: -0.1700

Data Index: 5943636 (Open Web Text)

Max Activating Token Index: 561

Text #8

Max Range: 1.9246. Min Range: -1.9246

Max Act: 1.8611. Min Act: -0.1700

Data Index: 3488618 (Open Web Text)

Max Activating Token Index: 285

Text #9

Max Range: 1.9246. Min Range: -1.9246

Max Act: 1.8403. Min Act: -0.1700

Data Index: 8574118 (Open Web Text)

Max Activating Token Index: 88

Text #10

Max Range: 1.9246. Min Range: -1.9246

Max Act: 1.8471. Min Act: -0.1700

Data Index: 7144600 (Open Web Text)

Max Activating Token Index: 285

Text #11

Max Range: 1.9246. Min Range: -1.9246

Max Act: 1.8519. Min Act: -0.1700

Data Index: 7123999 (Open Web Text)

Max Activating Token Index: 478

Text #12

Max Range: 1.9246. Min Range: -1.9246

Max Act: 1.8605. Min Act: -0.1700

Data Index: 4491779 (Open Web Text)

Max Activating Token Index: 45

Text #13

Max Range: 1.9246. Min Range: -1.9246

Max Act: 1.8192. Min Act: -0.1700

Data Index: 7926810 (Open Web Text)

Max Activating Token Index: 1018

Text #14

Max Range: 1.9246. Min Range: -1.9246

Max Act: 1.8433. Min Act: -0.1700

Data Index: 2983983 (Open Web Text)

Max Activating Token Index: 601

Text #15

Max Range: 1.9246. Min Range: -1.9246

Max Act: 1.8389. Min Act: -0.1700

Data Index: 1091161 (Open Web Text)

Max Activating Token Index: 783

Text #16

Max Range: 1.9246. Min Range: -1.9246

Max Act: 1.8289. Min Act: -0.1700

Data Index: 4336052 (Open Web Text)

Max Activating Token Index: 124

Text #17

Max Range: 1.9246. Min Range: -1.9246

Max Act: 1.8148. Min Act: -0.1700

Data Index: 6382660 (Open Web Text)

Max Activating Token Index: 225

Text #18

Max Range: 1.9246. Min Range: -1.9246

Max Act: 1.8308. Min Act: -0.1699

Data Index: 998000 (Open Web Text)

Max Activating Token Index: 798

Text #19

Max Range: 1.9246. Min Range: -1.9246

Max Act: 1.8046. Min Act: -0.1700

Data Index: 674122 (Open Web Text)

Max Activating Token Index: 130