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

Dataset: Open Web Text

Neuron 183 in Layer 0

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: 3.8823. Min Range: -3.8823

Max Act: 3.8823. Min Act: -0.1700

Data Index: 266403 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 3.8823. Min Range: -3.8823

Max Act: 3.8306. Min Act: -0.1700

Data Index: 8058749 (Open Web Text)

Max Activating Token Index: 14

Text #2

Max Range: 3.8823. Min Range: -3.8823

Max Act: 3.7963. Min Act: -0.1700

Data Index: 3992811 (Open Web Text)

Max Activating Token Index: 13

Text #3

Max Range: 3.8823. Min Range: -3.8823

Max Act: 3.8240. Min Act: -0.1700

Data Index: 2523104 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.8823. Min Range: -3.8823

Max Act: 3.7702. Min Act: -0.1700

Data Index: 2372537 (Open Web Text)

Max Activating Token Index: 19

Text #5

Max Range: 3.8823. Min Range: -3.8823

Max Act: 3.7835. Min Act: -0.1700

Data Index: 3347110 (Open Web Text)

Max Activating Token Index: 16

Text #6

Max Range: 3.8823. Min Range: -3.8823

Max Act: 3.7794. Min Act: -0.1700

Data Index: 3601243 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.8823. Min Range: -3.8823

Max Act: 3.7897. Min Act: -0.1700

Data Index: 7276365 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 3.8823. Min Range: -3.8823

Max Act: 3.7340. Min Act: -0.1700

Data Index: 4714892 (Open Web Text)

Max Activating Token Index: 71

Text #9

Max Range: 3.8823. Min Range: -3.8823

Max Act: 3.7337. Min Act: -0.1700

Data Index: 5483655 (Open Web Text)

Max Activating Token Index: 25

Text #10

Max Range: 3.8823. Min Range: -3.8823

Max Act: 3.7430. Min Act: -0.1700

Data Index: 2326781 (Open Web Text)

Max Activating Token Index: 54

Text #11

Max Range: 3.8823. Min Range: -3.8823

Max Act: 3.7441. Min Act: -0.1700

Data Index: 588673 (Open Web Text)

Max Activating Token Index: 120

Text #12

Max Range: 3.8823. Min Range: -3.8823

Max Act: 3.7358. Min Act: -0.1700

Data Index: 7605499 (Open Web Text)

Max Activating Token Index: 78

Text #13

Max Range: 3.8823. Min Range: -3.8823

Max Act: 3.7607. Min Act: -0.1700

Data Index: 6367098 (Open Web Text)

Max Activating Token Index: 9

Text #14

Max Range: 3.8823. Min Range: -3.8823

Max Act: 3.7596. Min Act: -0.1700

Data Index: 7599149 (Open Web Text)

Max Activating Token Index: 144

Text #15

Max Range: 3.8823. Min Range: -3.8823

Max Act: 3.7109. Min Act: -0.1700

Data Index: 3957928 (Open Web Text)

Max Activating Token Index: 13

Text #16

Max Range: 3.8823. Min Range: -3.8823

Max Act: 3.7255. Min Act: -0.1700

Data Index: 37119 (Open Web Text)

Max Activating Token Index: 10

Text #17

Max Range: 3.8823. Min Range: -3.8823

Max Act: 3.6998. Min Act: -0.1700

Data Index: 6889228 (Open Web Text)

Max Activating Token Index: 394

Text #18

Max Range: 3.8823. Min Range: -3.8823

Max Act: 3.7289. Min Act: -0.1700

Data Index: 3570547 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 3.8823. Min Range: -3.8823

Max Act: 3.7234. Min Act: -0.1700

Data Index: 2562490 (Open Web Text)

Max Activating Token Index: 46