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

Dataset: Open Web Text

Neuron 1710 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: 4.6656. Min Range: -4.6656

Max Act: 4.6656. Min Act: -0.1700

Data Index: 3427463 (Open Web Text)

Max Activating Token Index: 359

Text #1

Max Range: 4.6656. Min Range: -4.6656

Max Act: 4.6404. Min Act: -0.1700

Data Index: 6746205 (Open Web Text)

Max Activating Token Index: 107

Text #2

Max Range: 4.6656. Min Range: -4.6656

Max Act: 4.6044. Min Act: -0.1700

Data Index: 8264476 (Open Web Text)

Max Activating Token Index: 992

Text #3

Max Range: 4.6656. Min Range: -4.6656

Max Act: 4.6044. Min Act: -0.1700

Data Index: 5827020 (Open Web Text)

Max Activating Token Index: 381

Text #4

Max Range: 4.6656. Min Range: -4.6656

Max Act: 4.5610. Min Act: -0.1700

Data Index: 7072559 (Open Web Text)

Max Activating Token Index: 65

Text #5

Max Range: 4.6656. Min Range: -4.6656

Max Act: 4.5666. Min Act: -0.1700

Data Index: 4978300 (Open Web Text)

Max Activating Token Index: 137

Text #6

Max Range: 4.6656. Min Range: -4.6656

Max Act: 4.5573. Min Act: -0.1700

Data Index: 4749286 (Open Web Text)

Max Activating Token Index: 928

Text #7

Max Range: 4.6656. Min Range: -4.6656

Max Act: 4.5498. Min Act: -0.1700

Data Index: 177076 (Open Web Text)

Max Activating Token Index: 902

Text #8

Max Range: 4.6656. Min Range: -4.6656

Max Act: 4.5187. Min Act: -0.1700

Data Index: 5718290 (Open Web Text)

Max Activating Token Index: 899

Text #9

Max Range: 4.6656. Min Range: -4.6656

Max Act: 4.4987. Min Act: -0.1700

Data Index: 6976269 (Open Web Text)

Max Activating Token Index: 468

Text #10

Max Range: 4.6656. Min Range: -4.6656

Max Act: 4.5264. Min Act: -0.1700

Data Index: 1363622 (Open Web Text)

Max Activating Token Index: 95

Text #11

Max Range: 4.6656. Min Range: -4.6656

Max Act: 4.5293. Min Act: -0.1700

Data Index: 2826822 (Open Web Text)

Max Activating Token Index: 1014

Text #12

Max Range: 4.6656. Min Range: -4.6656

Max Act: 4.4609. Min Act: -0.1700

Data Index: 2836578 (Open Web Text)

Max Activating Token Index: 948

Text #13

Max Range: 4.6656. Min Range: -4.6656

Max Act: 4.4795. Min Act: -0.1700

Data Index: 6586548 (Open Web Text)

Max Activating Token Index: 158

Text #14

Max Range: 4.6656. Min Range: -4.6656

Max Act: 4.4804. Min Act: -0.1700

Data Index: 6624245 (Open Web Text)

Max Activating Token Index: 784

Text #15

Max Range: 4.6656. Min Range: -4.6656

Max Act: 4.4776. Min Act: -0.1700

Data Index: 6160979 (Open Web Text)

Max Activating Token Index: 282

Text #16

Max Range: 4.6656. Min Range: -4.6656

Max Act: 4.4775. Min Act: -0.1700

Data Index: 4384743 (Open Web Text)

Max Activating Token Index: 298

Text #17

Max Range: 4.6656. Min Range: -4.6656

Max Act: 4.5123. Min Act: -0.1700

Data Index: 6976270 (Open Web Text)

Max Activating Token Index: 515

Text #18

Max Range: 4.6656. Min Range: -4.6656

Max Act: 4.4352. Min Act: -0.1700

Data Index: 6409457 (Open Web Text)

Max Activating Token Index: 190

Text #19

Max Range: 4.6656. Min Range: -4.6656

Max Act: 4.4479. Min Act: -0.1700

Data Index: 1315597 (Open Web Text)

Max Activating Token Index: 836