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

Dataset: Open Web Text

Neuron 1469 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: 1.9496. Min Range: -1.9496

Max Act: 1.9496. Min Act: -0.1700

Data Index: 3903775 (Open Web Text)

Max Activating Token Index: 300

Text #1

Max Range: 1.9496. Min Range: -1.9496

Max Act: 1.9340. Min Act: -0.1700

Data Index: 764746 (Open Web Text)

Max Activating Token Index: 215

Text #2

Max Range: 1.9496. Min Range: -1.9496

Max Act: 1.8704. Min Act: -0.1700

Data Index: 3903788 (Open Web Text)

Max Activating Token Index: 548

Text #3

Max Range: 1.9496. Min Range: -1.9496

Max Act: 1.8529. Min Act: -0.1700

Data Index: 1203225 (Open Web Text)

Max Activating Token Index: 484

Text #4

Max Range: 1.9496. Min Range: -1.9496

Max Act: 1.8274. Min Act: -0.1700

Data Index: 402614 (Open Web Text)

Max Activating Token Index: 293

Text #5

Max Range: 1.9496. Min Range: -1.9496

Max Act: 1.8282. Min Act: -0.1700

Data Index: 161093 (Open Web Text)

Max Activating Token Index: 183

Text #6

Max Range: 1.9496. Min Range: -1.9496

Max Act: 1.8264. Min Act: -0.1700

Data Index: 6008023 (Open Web Text)

Max Activating Token Index: 443

Text #7

Max Range: 1.9496. Min Range: -1.9496

Max Act: 1.8266. Min Act: -0.1699

Data Index: 764742 (Open Web Text)

Max Activating Token Index: 487

Text #8

Max Range: 1.9496. Min Range: -1.9496

Max Act: 1.8200. Min Act: -0.1700

Data Index: 7545866 (Open Web Text)

Max Activating Token Index: 988

Text #9

Max Range: 1.9496. Min Range: -1.9496

Max Act: 1.8120. Min Act: -0.1700

Data Index: 3903765 (Open Web Text)

Max Activating Token Index: 407

Text #10

Max Range: 1.9496. Min Range: -1.9496

Max Act: 1.8132. Min Act: -0.1700

Data Index: 1184726 (Open Web Text)

Max Activating Token Index: 209

Text #11

Max Range: 1.9496. Min Range: -1.9496

Max Act: 1.8124. Min Act: -0.1700

Data Index: 764743 (Open Web Text)

Max Activating Token Index: 119

Text #12

Max Range: 1.9496. Min Range: -1.9496

Max Act: 1.8189. Min Act: -0.1700

Data Index: 3903758 (Open Web Text)

Max Activating Token Index: 136

Text #13

Max Range: 1.9496. Min Range: -1.9496

Max Act: 1.8086. Min Act: -0.1700

Data Index: 3707227 (Open Web Text)

Max Activating Token Index: 406

Text #14

Max Range: 1.9496. Min Range: -1.9496

Max Act: 1.8015. Min Act: -0.1700

Data Index: 3903789 (Open Web Text)

Max Activating Token Index: 500

Text #15

Max Range: 1.9496. Min Range: -1.9496

Max Act: 1.8200. Min Act: -0.1700

Data Index: 1184729 (Open Web Text)

Max Activating Token Index: 415

Text #16

Max Range: 1.9496. Min Range: -1.9496

Max Act: 1.8112. Min Act: -0.1700

Data Index: 1487445 (Open Web Text)

Max Activating Token Index: 347

Text #17

Max Range: 1.9496. Min Range: -1.9496

Max Act: 1.8132. Min Act: -0.1700

Data Index: 6717555 (Open Web Text)

Max Activating Token Index: 76

Text #18

Max Range: 1.9496. Min Range: -1.9496

Max Act: 1.8198. Min Act: -0.1700

Data Index: 1487430 (Open Web Text)

Max Activating Token Index: 657

Text #19

Max Range: 1.9496. Min Range: -1.9496

Max Act: 1.8109. Min Act: -0.1700

Data Index: 1449887 (Open Web Text)

Max Activating Token Index: 587