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

Dataset: Open Web Text

Neuron 521 in Layer 1

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: 3.6660. Min Range: -3.6660

Max Act: 3.6622. Min Act: -0.1700

Data Index: 7558416 (Open Web Text)

Max Activating Token Index: 113

Text #1

Max Range: 3.6660. Min Range: -3.6660

Max Act: 3.6414. Min Act: -0.1700

Data Index: 7499261 (Open Web Text)

Max Activating Token Index: 295

Text #2

Max Range: 3.6660. Min Range: -3.6660

Max Act: 3.6449. Min Act: -0.1700

Data Index: 2240618 (Open Web Text)

Max Activating Token Index: 188

Text #3

Max Range: 3.6660. Min Range: -3.6660

Max Act: 3.6660. Min Act: -0.1700

Data Index: 6139947 (Open Web Text)

Max Activating Token Index: 318

Text #4

Max Range: 3.6660. Min Range: -3.6660

Max Act: 3.6178. Min Act: -0.1700

Data Index: 2434333 (Open Web Text)

Max Activating Token Index: 617

Text #5

Max Range: 3.6660. Min Range: -3.6660

Max Act: 3.6469. Min Act: -0.1700

Data Index: 192820 (Open Web Text)

Max Activating Token Index: 548

Text #6

Max Range: 3.6660. Min Range: -3.6660

Max Act: 3.6303. Min Act: -0.1700

Data Index: 2430603 (Open Web Text)

Max Activating Token Index: 91

Text #7

Max Range: 3.6660. Min Range: -3.6660

Max Act: 3.6232. Min Act: -0.1700

Data Index: 4194745 (Open Web Text)

Max Activating Token Index: 248

Text #8

Max Range: 3.6660. Min Range: -3.6660

Max Act: 3.6180. Min Act: -0.1700

Data Index: 5186105 (Open Web Text)

Max Activating Token Index: 223

Text #9

Max Range: 3.6660. Min Range: -3.6660

Max Act: 3.6062. Min Act: -0.1700

Data Index: 101872 (Open Web Text)

Max Activating Token Index: 554

Text #10

Max Range: 3.6660. Min Range: -3.6660

Max Act: 3.6389. Min Act: -0.1700

Data Index: 4959160 (Open Web Text)

Max Activating Token Index: 715

Text #11

Max Range: 3.6660. Min Range: -3.6660

Max Act: 3.6353. Min Act: -0.1700

Data Index: 8318491 (Open Web Text)

Max Activating Token Index: 786

Text #12

Max Range: 3.6660. Min Range: -3.6660

Max Act: 3.5959. Min Act: -0.1700

Data Index: 2073042 (Open Web Text)

Max Activating Token Index: 245

Text #13

Max Range: 3.6660. Min Range: -3.6660

Max Act: 3.5955. Min Act: -0.1700

Data Index: 5766677 (Open Web Text)

Max Activating Token Index: 338

Text #14

Max Range: 3.6660. Min Range: -3.6660

Max Act: 3.5946. Min Act: -0.1700

Data Index: 6228843 (Open Web Text)

Max Activating Token Index: 533

Text #15

Max Range: 3.6660. Min Range: -3.6660

Max Act: 3.6130. Min Act: -0.1700

Data Index: 3854549 (Open Web Text)

Max Activating Token Index: 621

Text #16

Max Range: 3.6660. Min Range: -3.6660

Max Act: 3.5941. Min Act: -0.1700

Data Index: 5982864 (Open Web Text)

Max Activating Token Index: 42

Text #17

Max Range: 3.6660. Min Range: -3.6660

Max Act: 3.6078. Min Act: -0.1700

Data Index: 4088316 (Open Web Text)

Max Activating Token Index: 633

Text #18

Max Range: 3.6660. Min Range: -3.6660

Max Act: 3.6134. Min Act: -0.1700

Data Index: 6396376 (Open Web Text)

Max Activating Token Index: 561

Text #19

Max Range: 3.6660. Min Range: -3.6660

Max Act: 3.6021. Min Act: -0.1700

Data Index: 538275 (Open Web Text)

Max Activating Token Index: 370