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

Dataset: Open Web Text

Neuron 2059 in Layer 4

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: 4.5593. Min Range: -4.5593

Max Act: 4.5593. Min Act: -0.1700

Data Index: 4613134 (Open Web Text)

Max Activating Token Index: 772

Text #1

Max Range: 4.5593. Min Range: -4.5593

Max Act: 4.4089. Min Act: -0.1700

Data Index: 8256701 (Open Web Text)

Max Activating Token Index: 974

Text #2

Max Range: 4.5593. Min Range: -4.5593

Max Act: 4.3655. Min Act: -0.1700

Data Index: 2485892 (Open Web Text)

Max Activating Token Index: 744

Text #3

Max Range: 4.5593. Min Range: -4.5593

Max Act: 4.3559. Min Act: -0.1700

Data Index: 7233067 (Open Web Text)

Max Activating Token Index: 571

Text #4

Max Range: 4.5593. Min Range: -4.5593

Max Act: 4.3394. Min Act: -0.1700

Data Index: 6179266 (Open Web Text)

Max Activating Token Index: 173

Text #5

Max Range: 4.5593. Min Range: -4.5593

Max Act: 4.3673. Min Act: -0.1700

Data Index: 1924465 (Open Web Text)

Max Activating Token Index: 1022

Text #6

Max Range: 4.5593. Min Range: -4.5593

Max Act: 4.2559. Min Act: -0.1700

Data Index: 856239 (Open Web Text)

Max Activating Token Index: 970

Text #7

Max Range: 4.5593. Min Range: -4.5593

Max Act: 4.2254. Min Act: -0.1700

Data Index: 3788184 (Open Web Text)

Max Activating Token Index: 719

Text #8

Max Range: 4.5593. Min Range: -4.5593

Max Act: 4.1961. Min Act: -0.1700

Data Index: 4920922 (Open Web Text)

Max Activating Token Index: 409

Text #9

Max Range: 4.5593. Min Range: -4.5593

Max Act: 4.2213. Min Act: -0.1700

Data Index: 4346648 (Open Web Text)

Max Activating Token Index: 587

Text #10

Max Range: 4.5593. Min Range: -4.5593

Max Act: 4.1946. Min Act: -0.1700

Data Index: 2314822 (Open Web Text)

Max Activating Token Index: 268

Text #11

Max Range: 4.5593. Min Range: -4.5593

Max Act: 4.1653. Min Act: -0.1700

Data Index: 2249372 (Open Web Text)

Max Activating Token Index: 40

Text #12

Max Range: 4.5593. Min Range: -4.5593

Max Act: 4.1405. Min Act: -0.1700

Data Index: 4130201 (Open Web Text)

Max Activating Token Index: 679

Text #13

Max Range: 4.5593. Min Range: -4.5593

Max Act: 4.1483. Min Act: -0.1700

Data Index: 8675294 (Open Web Text)

Max Activating Token Index: 61

Text #14

Max Range: 4.5593. Min Range: -4.5593

Max Act: 4.1583. Min Act: -0.1700

Data Index: 4623106 (Open Web Text)

Max Activating Token Index: 443

Text #15

Max Range: 4.5593. Min Range: -4.5593

Max Act: 4.1464. Min Act: -0.1700

Data Index: 8279912 (Open Web Text)

Max Activating Token Index: 366

Text #16

Max Range: 4.5593. Min Range: -4.5593

Max Act: 4.1710. Min Act: -0.1700

Data Index: 2352890 (Open Web Text)

Max Activating Token Index: 282

Text #17

Max Range: 4.5593. Min Range: -4.5593

Max Act: 4.1471. Min Act: -0.1700

Data Index: 1036697 (Open Web Text)

Max Activating Token Index: 685

Text #18

Max Range: 4.5593. Min Range: -4.5593

Max Act: 4.0859. Min Act: -0.1700

Data Index: 4144409 (Open Web Text)

Max Activating Token Index: 601

Text #19

Max Range: 4.5593. Min Range: -4.5593

Max Act: 4.1204. Min Act: -0.1700

Data Index: 3204998 (Open Web Text)

Max Activating Token Index: 71