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

Dataset: Open Web Text

Neuron 197 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: 3.3753. Min Range: -3.3753

Max Act: 3.3753. Min Act: -0.1700

Data Index: 144154 (Open Web Text)

Max Activating Token Index: 218

Text #1

Max Range: 3.3753. Min Range: -3.3753

Max Act: 3.3549. Min Act: -0.1700

Data Index: 7291605 (Open Web Text)

Max Activating Token Index: 329

Text #2

Max Range: 3.3753. Min Range: -3.3753

Max Act: 3.3163. Min Act: -0.1700

Data Index: 8384314 (Open Web Text)

Max Activating Token Index: 838

Text #3

Max Range: 3.3753. Min Range: -3.3753

Max Act: 3.3102. Min Act: -0.1700

Data Index: 3367138 (Open Web Text)

Max Activating Token Index: 203

Text #4

Max Range: 3.3753. Min Range: -3.3753

Max Act: 3.2468. Min Act: -0.1700

Data Index: 7803234 (Open Web Text)

Max Activating Token Index: 988

Text #5

Max Range: 3.3753. Min Range: -3.3753

Max Act: 3.2549. Min Act: -0.1700

Data Index: 3237614 (Open Web Text)

Max Activating Token Index: 377

Text #6

Max Range: 3.3753. Min Range: -3.3753

Max Act: 3.2029. Min Act: -0.1700

Data Index: 803289 (Open Web Text)

Max Activating Token Index: 212

Text #7

Max Range: 3.3753. Min Range: -3.3753

Max Act: 3.2207. Min Act: -0.1700

Data Index: 6738499 (Open Web Text)

Max Activating Token Index: 566

Text #8

Max Range: 3.3753. Min Range: -3.3753

Max Act: 3.2131. Min Act: -0.1700

Data Index: 6637625 (Open Web Text)

Max Activating Token Index: 492

Text #9

Max Range: 3.3753. Min Range: -3.3753

Max Act: 3.2311. Min Act: -0.1700

Data Index: 2905482 (Open Web Text)

Max Activating Token Index: 801

Text #10

Max Range: 3.3753. Min Range: -3.3753

Max Act: 3.2084. Min Act: -0.1700

Data Index: 8796998 (Open Web Text)

Max Activating Token Index: 839

Text #11

Max Range: 3.3753. Min Range: -3.3753

Max Act: 3.2032. Min Act: -0.1700

Data Index: 3733135 (Open Web Text)

Max Activating Token Index: 274

Text #12

Max Range: 3.3753. Min Range: -3.3753

Max Act: 3.2130. Min Act: -0.1700

Data Index: 1404208 (Open Web Text)

Max Activating Token Index: 117

Text #13

Max Range: 3.3753. Min Range: -3.3753

Max Act: 3.2110. Min Act: -0.1700

Data Index: 302142 (Open Web Text)

Max Activating Token Index: 199

Text #14

Max Range: 3.3753. Min Range: -3.3753

Max Act: 3.2073. Min Act: -0.1700

Data Index: 3236215 (Open Web Text)

Max Activating Token Index: 762

Text #15

Max Range: 3.3753. Min Range: -3.3753

Max Act: 3.2273. Min Act: -0.1700

Data Index: 7426681 (Open Web Text)

Max Activating Token Index: 777

Text #16

Max Range: 3.3753. Min Range: -3.3753

Max Act: 3.1875. Min Act: -0.1700

Data Index: 2467302 (Open Web Text)

Max Activating Token Index: 956

Text #17

Max Range: 3.3753. Min Range: -3.3753

Max Act: 3.1974. Min Act: -0.1700

Data Index: 6796299 (Open Web Text)

Max Activating Token Index: 282

Text #18

Max Range: 3.3753. Min Range: -3.3753

Max Act: 3.1870. Min Act: -0.1700

Data Index: 2467790 (Open Web Text)

Max Activating Token Index: 187

Text #19

Max Range: 3.3753. Min Range: -3.3753

Max Act: 3.1700. Min Act: -0.1700

Data Index: 878395 (Open Web Text)

Max Activating Token Index: 583