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

Dataset: Open Web Text

Neuron 1228 in Layer 6

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: 2.5325. Min Range: -2.5325

Max Act: 2.5325. Min Act: -0.1700

Data Index: 1611979 (Open Web Text)

Max Activating Token Index: 309

Text #1

Max Range: 2.5325. Min Range: -2.5325

Max Act: 2.5238. Min Act: -0.1700

Data Index: 8735794 (Open Web Text)

Max Activating Token Index: 594

Text #2

Max Range: 2.5325. Min Range: -2.5325

Max Act: 2.5162. Min Act: -0.1700

Data Index: 1836352 (Open Web Text)

Max Activating Token Index: 497

Text #3

Max Range: 2.5325. Min Range: -2.5325

Max Act: 2.4930. Min Act: -0.1700

Data Index: 1843461 (Open Web Text)

Max Activating Token Index: 305

Text #4

Max Range: 2.5325. Min Range: -2.5325

Max Act: 2.4956. Min Act: -0.1700

Data Index: 3931474 (Open Web Text)

Max Activating Token Index: 984

Text #5

Max Range: 2.5325. Min Range: -2.5325

Max Act: 2.5176. Min Act: -0.1700

Data Index: 399906 (Open Web Text)

Max Activating Token Index: 676

Text #6

Max Range: 2.5325. Min Range: -2.5325

Max Act: 2.5144. Min Act: -0.1700

Data Index: 3417728 (Open Web Text)

Max Activating Token Index: 386

Text #7

Max Range: 2.5325. Min Range: -2.5325

Max Act: 2.4943. Min Act: -0.1700

Data Index: 6352036 (Open Web Text)

Max Activating Token Index: 446

Text #8

Max Range: 2.5325. Min Range: -2.5325

Max Act: 2.4617. Min Act: -0.1700

Data Index: 3726810 (Open Web Text)

Max Activating Token Index: 1011

Text #9

Max Range: 2.5325. Min Range: -2.5325

Max Act: 2.4682. Min Act: -0.1700

Data Index: 11043 (Open Web Text)

Max Activating Token Index: 967

Text #10

Max Range: 2.5325. Min Range: -2.5325

Max Act: 2.4525. Min Act: -0.1700

Data Index: 5279114 (Open Web Text)

Max Activating Token Index: 511

Text #11

Max Range: 2.5325. Min Range: -2.5325

Max Act: 2.4610. Min Act: -0.1700

Data Index: 566173 (Open Web Text)

Max Activating Token Index: 1019

Text #12

Max Range: 2.5325. Min Range: -2.5325

Max Act: 2.4369. Min Act: -0.1700

Data Index: 6854084 (Open Web Text)

Max Activating Token Index: 325

Text #13

Max Range: 2.5325. Min Range: -2.5325

Max Act: 2.4617. Min Act: -0.1700

Data Index: 2285082 (Open Web Text)

Max Activating Token Index: 318

Text #14

Max Range: 2.5325. Min Range: -2.5325

Max Act: 2.4411. Min Act: -0.1700

Data Index: 4099740 (Open Web Text)

Max Activating Token Index: 400

Text #15

Max Range: 2.5325. Min Range: -2.5325

Max Act: 2.4316. Min Act: -0.1700

Data Index: 7308338 (Open Web Text)

Max Activating Token Index: 312

Text #16

Max Range: 2.5325. Min Range: -2.5325

Max Act: 2.4329. Min Act: -0.1700

Data Index: 8459609 (Open Web Text)

Max Activating Token Index: 632

Text #17

Max Range: 2.5325. Min Range: -2.5325

Max Act: 2.4480. Min Act: -0.1700

Data Index: 4709274 (Open Web Text)

Max Activating Token Index: 475

Text #18

Max Range: 2.5325. Min Range: -2.5325

Max Act: 2.4321. Min Act: -0.1700

Data Index: 1031232 (Open Web Text)

Max Activating Token Index: 540

Text #19

Max Range: 2.5325. Min Range: -2.5325

Max Act: 2.4342. Min Act: -0.1700

Data Index: 2110592 (Open Web Text)

Max Activating Token Index: 1011