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

Dataset: Open Web Text

Neuron 1198 in Layer 5

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: 4.2240. Min Range: -4.2240

Max Act: 4.2240. Min Act: -0.1700

Data Index: 1299421 (Open Web Text)

Max Activating Token Index: 950

Text #1

Max Range: 4.2240. Min Range: -4.2240

Max Act: 4.2059. Min Act: -0.1700

Data Index: 7824342 (Open Web Text)

Max Activating Token Index: 482

Text #2

Max Range: 4.2240. Min Range: -4.2240

Max Act: 4.1894. Min Act: -0.1700

Data Index: 1426244 (Open Web Text)

Max Activating Token Index: 232

Text #3

Max Range: 4.2240. Min Range: -4.2240

Max Act: 4.1764. Min Act: -0.1700

Data Index: 1761211 (Open Web Text)

Max Activating Token Index: 909

Text #4

Max Range: 4.2240. Min Range: -4.2240

Max Act: 4.0829. Min Act: -0.1700

Data Index: 1115634 (Open Web Text)

Max Activating Token Index: 801

Text #5

Max Range: 4.2240. Min Range: -4.2240

Max Act: 4.0477. Min Act: -0.1700

Data Index: 2785419 (Open Web Text)

Max Activating Token Index: 633

Text #6

Max Range: 4.2240. Min Range: -4.2240

Max Act: 3.9981. Min Act: -0.1700

Data Index: 5138284 (Open Web Text)

Max Activating Token Index: 643

Text #7

Max Range: 4.2240. Min Range: -4.2240

Max Act: 4.0426. Min Act: -0.1700

Data Index: 5138282 (Open Web Text)

Max Activating Token Index: 666

Text #8

Max Range: 4.2240. Min Range: -4.2240

Max Act: 3.9870. Min Act: -0.1700

Data Index: 1722263 (Open Web Text)

Max Activating Token Index: 507

Text #9

Max Range: 4.2240. Min Range: -4.2240

Max Act: 4.0109. Min Act: -0.1700

Data Index: 8516811 (Open Web Text)

Max Activating Token Index: 331

Text #10

Max Range: 4.2240. Min Range: -4.2240

Max Act: 3.9938. Min Act: -0.1700

Data Index: 2523303 (Open Web Text)

Max Activating Token Index: 709

Text #11

Max Range: 4.2240. Min Range: -4.2240

Max Act: 4.0082. Min Act: -0.1700

Data Index: 7437980 (Open Web Text)

Max Activating Token Index: 14

Text #12

Max Range: 4.2240. Min Range: -4.2240

Max Act: 4.0184. Min Act: -0.1700

Data Index: 7092629 (Open Web Text)

Max Activating Token Index: 354

Text #13

Max Range: 4.2240. Min Range: -4.2240

Max Act: 4.0293. Min Act: -0.1700

Data Index: 1355416 (Open Web Text)

Max Activating Token Index: 529

Text #14

Max Range: 4.2240. Min Range: -4.2240

Max Act: 4.0376. Min Act: -0.1700

Data Index: 5908411 (Open Web Text)

Max Activating Token Index: 961

Text #15

Max Range: 4.2240. Min Range: -4.2240

Max Act: 3.9934. Min Act: -0.1700

Data Index: 1774037 (Open Web Text)

Max Activating Token Index: 256

Text #16

Max Range: 4.2240. Min Range: -4.2240

Max Act: 4.0009. Min Act: -0.1700

Data Index: 3956922 (Open Web Text)

Max Activating Token Index: 236

Text #17

Max Range: 4.2240. Min Range: -4.2240

Max Act: 3.9453. Min Act: -0.1700

Data Index: 4113538 (Open Web Text)

Max Activating Token Index: 756

Text #18

Max Range: 4.2240. Min Range: -4.2240

Max Act: 3.9889. Min Act: -0.1700

Data Index: 807177 (Open Web Text)

Max Activating Token Index: 307

Text #19

Max Range: 4.2240. Min Range: -4.2240

Max Act: 3.9787. Min Act: -0.1700

Data Index: 1656059 (Open Web Text)

Max Activating Token Index: 578