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

Dataset: Open Web Text

Neuron 2830 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: 6.6656. Min Range: -6.6656

Max Act: 6.6656. Min Act: -0.1700

Data Index: 6752150 (Open Web Text)

Max Activating Token Index: 648

Text #1

Max Range: 6.6656. Min Range: -6.6656

Max Act: 6.5399. Min Act: -0.1700

Data Index: 6388560 (Open Web Text)

Max Activating Token Index: 159

Text #2

Max Range: 6.6656. Min Range: -6.6656

Max Act: 6.5118. Min Act: -0.1700

Data Index: 4392961 (Open Web Text)

Max Activating Token Index: 630

Text #3

Max Range: 6.6656. Min Range: -6.6656

Max Act: 6.5547. Min Act: -0.1700

Data Index: 3034529 (Open Web Text)

Max Activating Token Index: 483

Text #4

Max Range: 6.6656. Min Range: -6.6656

Max Act: 6.5156. Min Act: -0.1700

Data Index: 6037606 (Open Web Text)

Max Activating Token Index: 646

Text #5

Max Range: 6.6656. Min Range: -6.6656

Max Act: 6.4943. Min Act: -0.1700

Data Index: 6272397 (Open Web Text)

Max Activating Token Index: 645

Text #6

Max Range: 6.6656. Min Range: -6.6656

Max Act: 6.4430. Min Act: -0.1700

Data Index: 6179192 (Open Web Text)

Max Activating Token Index: 731

Text #7

Max Range: 6.6656. Min Range: -6.6656

Max Act: 6.4199. Min Act: -0.1700

Data Index: 3936394 (Open Web Text)

Max Activating Token Index: 516

Text #8

Max Range: 6.6656. Min Range: -6.6656

Max Act: 6.4410. Min Act: -0.1700

Data Index: 7538009 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 6.6656. Min Range: -6.6656

Max Act: 6.4248. Min Act: -0.1700

Data Index: 7574687 (Open Web Text)

Max Activating Token Index: 372

Text #10

Max Range: 6.6656. Min Range: -6.6656

Max Act: 6.4338. Min Act: -0.1700

Data Index: 1770589 (Open Web Text)

Max Activating Token Index: 777

Text #11

Max Range: 6.6656. Min Range: -6.6656

Max Act: 6.4397. Min Act: -0.1700

Data Index: 5855901 (Open Web Text)

Max Activating Token Index: 988

Text #12

Max Range: 6.6656. Min Range: -6.6656

Max Act: 6.3606. Min Act: -0.1700

Data Index: 3906523 (Open Web Text)

Max Activating Token Index: 429

Text #13

Max Range: 6.6656. Min Range: -6.6656

Max Act: 6.4373. Min Act: -0.1700

Data Index: 4951874 (Open Web Text)

Max Activating Token Index: 996

Text #14

Max Range: 6.6656. Min Range: -6.6656

Max Act: 6.4483. Min Act: -0.1700

Data Index: 471785 (Open Web Text)

Max Activating Token Index: 1010

Text #15

Max Range: 6.6656. Min Range: -6.6656

Max Act: 6.3424. Min Act: -0.1700

Data Index: 6813128 (Open Web Text)

Max Activating Token Index: 175

Text #16

Max Range: 6.6656. Min Range: -6.6656

Max Act: 6.4598. Min Act: -0.1700

Data Index: 1485378 (Open Web Text)

Max Activating Token Index: 488

Text #17

Max Range: 6.6656. Min Range: -6.6656

Max Act: 6.4365. Min Act: -0.1700

Data Index: 1334226 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 6.6656. Min Range: -6.6656

Max Act: 6.3839. Min Act: -0.1700

Data Index: 6096477 (Open Web Text)

Max Activating Token Index: 449

Text #19

Max Range: 6.6656. Min Range: -6.6656

Max Act: 6.3788. Min Act: -0.1700

Data Index: 1940696 (Open Web Text)

Max Activating Token Index: 1011