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

Dataset: Open Web Text

Neuron 2289 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: 4.3797. Min Range: -4.3797

Max Act: 4.3797. Min Act: -0.1700

Data Index: 2954603 (Open Web Text)

Max Activating Token Index: 897

Text #1

Max Range: 4.3797. Min Range: -4.3797

Max Act: 4.3221. Min Act: -0.1700

Data Index: 2153291 (Open Web Text)

Max Activating Token Index: 880

Text #2

Max Range: 4.3797. Min Range: -4.3797

Max Act: 4.2725. Min Act: -0.1700

Data Index: 8263025 (Open Web Text)

Max Activating Token Index: 422

Text #3

Max Range: 4.3797. Min Range: -4.3797

Max Act: 4.2661. Min Act: -0.1700

Data Index: 3862616 (Open Web Text)

Max Activating Token Index: 250

Text #4

Max Range: 4.3797. Min Range: -4.3797

Max Act: 4.2384. Min Act: -0.1700

Data Index: 916193 (Open Web Text)

Max Activating Token Index: 840

Text #5

Max Range: 4.3797. Min Range: -4.3797

Max Act: 4.1976. Min Act: -0.1700

Data Index: 3225973 (Open Web Text)

Max Activating Token Index: 467

Text #6

Max Range: 4.3797. Min Range: -4.3797

Max Act: 4.1946. Min Act: -0.1700

Data Index: 3428217 (Open Web Text)

Max Activating Token Index: 153

Text #7

Max Range: 4.3797. Min Range: -4.3797

Max Act: 4.1775. Min Act: -0.1700

Data Index: 3862615 (Open Web Text)

Max Activating Token Index: 707

Text #8

Max Range: 4.3797. Min Range: -4.3797

Max Act: 4.1617. Min Act: -0.1700

Data Index: 5406016 (Open Web Text)

Max Activating Token Index: 981

Text #9

Max Range: 4.3797. Min Range: -4.3797

Max Act: 4.1489. Min Act: -0.1700

Data Index: 8581791 (Open Web Text)

Max Activating Token Index: 870

Text #10

Max Range: 4.3797. Min Range: -4.3797

Max Act: 4.1374. Min Act: -0.1700

Data Index: 2708511 (Open Web Text)

Max Activating Token Index: 297

Text #11

Max Range: 4.3797. Min Range: -4.3797

Max Act: 4.1088. Min Act: -0.1700

Data Index: 4237460 (Open Web Text)

Max Activating Token Index: 296

Text #12

Max Range: 4.3797. Min Range: -4.3797

Max Act: 4.1434. Min Act: -0.1700

Data Index: 6564389 (Open Web Text)

Max Activating Token Index: 896

Text #13

Max Range: 4.3797. Min Range: -4.3797

Max Act: 4.1547. Min Act: -0.1700

Data Index: 1698045 (Open Web Text)

Max Activating Token Index: 42

Text #14

Max Range: 4.3797. Min Range: -4.3797

Max Act: 4.1283. Min Act: -0.1700

Data Index: 45467 (Open Web Text)

Max Activating Token Index: 537

Text #15

Max Range: 4.3797. Min Range: -4.3797

Max Act: 4.1216. Min Act: -0.1700

Data Index: 8727049 (Open Web Text)

Max Activating Token Index: 343

Text #16

Max Range: 4.3797. Min Range: -4.3797

Max Act: 4.1464. Min Act: -0.1700

Data Index: 1726230 (Open Web Text)

Max Activating Token Index: 613

Text #17

Max Range: 4.3797. Min Range: -4.3797

Max Act: 4.0998. Min Act: -0.1700

Data Index: 1366482 (Open Web Text)

Max Activating Token Index: 1000

Text #18

Max Range: 4.3797. Min Range: -4.3797

Max Act: 4.1134. Min Act: -0.1700

Data Index: 1876196 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 4.3797. Min Range: -4.3797

Max Act: 4.0952. Min Act: -0.1700

Data Index: 4770838 (Open Web Text)

Max Activating Token Index: 180