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

Dataset: Open Web Text

Neuron 1068 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: 4.3064. Min Range: -4.3064

Max Act: 4.3064. Min Act: -0.1700

Data Index: 3487750 (Open Web Text)

Max Activating Token Index: 220

Text #1

Max Range: 4.3064. Min Range: -4.3064

Max Act: 4.2726. Min Act: -0.1700

Data Index: 8658861 (Open Web Text)

Max Activating Token Index: 205

Text #2

Max Range: 4.3064. Min Range: -4.3064

Max Act: 4.2503. Min Act: -0.1700

Data Index: 1103833 (Open Web Text)

Max Activating Token Index: 666

Text #3

Max Range: 4.3064. Min Range: -4.3064

Max Act: 4.2795. Min Act: -0.1700

Data Index: 4609273 (Open Web Text)

Max Activating Token Index: 708

Text #4

Max Range: 4.3064. Min Range: -4.3064

Max Act: 4.2219. Min Act: -0.1700

Data Index: 215979 (Open Web Text)

Max Activating Token Index: 892

Text #5

Max Range: 4.3064. Min Range: -4.3064

Max Act: 4.1954. Min Act: -0.1700

Data Index: 221785 (Open Web Text)

Max Activating Token Index: 573

Text #6

Max Range: 4.3064. Min Range: -4.3064

Max Act: 4.1830. Min Act: -0.1700

Data Index: 7894489 (Open Web Text)

Max Activating Token Index: 936

Text #7

Max Range: 4.3064. Min Range: -4.3064

Max Act: 4.1710. Min Act: -0.1700

Data Index: 4278839 (Open Web Text)

Max Activating Token Index: 291

Text #8

Max Range: 4.3064. Min Range: -4.3064

Max Act: 4.1434. Min Act: -0.1700

Data Index: 7046633 (Open Web Text)

Max Activating Token Index: 633

Text #9

Max Range: 4.3064. Min Range: -4.3064

Max Act: 4.1571. Min Act: -0.1700

Data Index: 4879497 (Open Web Text)

Max Activating Token Index: 568

Text #10

Max Range: 4.3064. Min Range: -4.3064

Max Act: 4.1678. Min Act: -0.1700

Data Index: 8454049 (Open Web Text)

Max Activating Token Index: 133

Text #11

Max Range: 4.3064. Min Range: -4.3064

Max Act: 4.1769. Min Act: -0.1700

Data Index: 5041847 (Open Web Text)

Max Activating Token Index: 647

Text #12

Max Range: 4.3064. Min Range: -4.3064

Max Act: 4.1210. Min Act: -0.1700

Data Index: 8684868 (Open Web Text)

Max Activating Token Index: 620

Text #13

Max Range: 4.3064. Min Range: -4.3064

Max Act: 4.1405. Min Act: -0.1700

Data Index: 3418506 (Open Web Text)

Max Activating Token Index: 300

Text #14

Max Range: 4.3064. Min Range: -4.3064

Max Act: 4.1333. Min Act: -0.1700

Data Index: 8626037 (Open Web Text)

Max Activating Token Index: 244

Text #15

Max Range: 4.3064. Min Range: -4.3064

Max Act: 4.1467. Min Act: -0.1700

Data Index: 7067778 (Open Web Text)

Max Activating Token Index: 776

Text #16

Max Range: 4.3064. Min Range: -4.3064

Max Act: 4.1197. Min Act: -0.1700

Data Index: 7076779 (Open Web Text)

Max Activating Token Index: 838

Text #17

Max Range: 4.3064. Min Range: -4.3064

Max Act: 4.0991. Min Act: -0.1700

Data Index: 919426 (Open Web Text)

Max Activating Token Index: 860

Text #18

Max Range: 4.3064. Min Range: -4.3064

Max Act: 4.1013. Min Act: -0.1700

Data Index: 2883081 (Open Web Text)

Max Activating Token Index: 617

Text #19

Max Range: 4.3064. Min Range: -4.3064

Max Act: 4.0716. Min Act: -0.1700

Data Index: 5072743 (Open Web Text)

Max Activating Token Index: 661