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

Dataset: Open Web Text

Neuron 826 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: 5.3964. Min Range: -5.3964

Max Act: 5.3964. Min Act: -0.1700

Data Index: 7316491 (Open Web Text)

Max Activating Token Index: 456

Text #1

Max Range: 5.3964. Min Range: -5.3964

Max Act: 5.3477. Min Act: -0.1700

Data Index: 2850602 (Open Web Text)

Max Activating Token Index: 427

Text #2

Max Range: 5.3964. Min Range: -5.3964

Max Act: 5.2894. Min Act: -0.1700

Data Index: 4226165 (Open Web Text)

Max Activating Token Index: 360

Text #3

Max Range: 5.3964. Min Range: -5.3964

Max Act: 5.2340. Min Act: -0.1700

Data Index: 4464984 (Open Web Text)

Max Activating Token Index: 243

Text #4

Max Range: 5.3964. Min Range: -5.3964

Max Act: 5.1694. Min Act: -0.1700

Data Index: 6620413 (Open Web Text)

Max Activating Token Index: 341

Text #5

Max Range: 5.3964. Min Range: -5.3964

Max Act: 5.1778. Min Act: -0.1700

Data Index: 15111 (Open Web Text)

Max Activating Token Index: 869

Text #6

Max Range: 5.3964. Min Range: -5.3964

Max Act: 5.1738. Min Act: -0.1700

Data Index: 2789594 (Open Web Text)

Max Activating Token Index: 392

Text #7

Max Range: 5.3964. Min Range: -5.3964

Max Act: 5.1427. Min Act: -0.1700

Data Index: 2659591 (Open Web Text)

Max Activating Token Index: 308

Text #8

Max Range: 5.3964. Min Range: -5.3964

Max Act: 5.1454. Min Act: -0.1700

Data Index: 7076176 (Open Web Text)

Max Activating Token Index: 954

Text #9

Max Range: 5.3964. Min Range: -5.3964

Max Act: 5.1593. Min Act: -0.1700

Data Index: 6853842 (Open Web Text)

Max Activating Token Index: 292

Text #10

Max Range: 5.3964. Min Range: -5.3964

Max Act: 5.1709. Min Act: -0.1700

Data Index: 6692443 (Open Web Text)

Max Activating Token Index: 195

Text #11

Max Range: 5.3964. Min Range: -5.3964

Max Act: 5.1671. Min Act: -0.1700

Data Index: 1053140 (Open Web Text)

Max Activating Token Index: 888

Text #12

Max Range: 5.3964. Min Range: -5.3964

Max Act: 5.1325. Min Act: -0.1700

Data Index: 5462281 (Open Web Text)

Max Activating Token Index: 176

Text #13

Max Range: 5.3964. Min Range: -5.3964

Max Act: 5.1573. Min Act: -0.1700

Data Index: 7348118 (Open Web Text)

Max Activating Token Index: 54

Text #14

Max Range: 5.3964. Min Range: -5.3964

Max Act: 5.1396. Min Act: -0.1700

Data Index: 4240265 (Open Web Text)

Max Activating Token Index: 426

Text #15

Max Range: 5.3964. Min Range: -5.3964

Max Act: 5.1654. Min Act: -0.1700

Data Index: 5225230 (Open Web Text)

Max Activating Token Index: 982

Text #16

Max Range: 5.3964. Min Range: -5.3964

Max Act: 5.1036. Min Act: -0.1700

Data Index: 6969475 (Open Web Text)

Max Activating Token Index: 101

Text #17

Max Range: 5.3964. Min Range: -5.3964

Max Act: 5.1040. Min Act: -0.1700

Data Index: 2221668 (Open Web Text)

Max Activating Token Index: 584

Text #18

Max Range: 5.3964. Min Range: -5.3964

Max Act: 5.1110. Min Act: -0.1700

Data Index: 5273151 (Open Web Text)

Max Activating Token Index: 689

Text #19

Max Range: 5.3964. Min Range: -5.3964

Max Act: 5.0965. Min Act: -0.1700

Data Index: 8037439 (Open Web Text)

Max Activating Token Index: 430