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

Dataset: Open Web Text

Neuron 735 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: 4.6824. Min Range: -4.6824

Max Act: 4.6824. Min Act: -0.1700

Data Index: 1930596 (Open Web Text)

Max Activating Token Index: 243

Text #1

Max Range: 4.6824. Min Range: -4.6824

Max Act: 4.5792. Min Act: -0.1700

Data Index: 1714533 (Open Web Text)

Max Activating Token Index: 411

Text #2

Max Range: 4.6824. Min Range: -4.6824

Max Act: 4.4665. Min Act: -0.1700

Data Index: 4082194 (Open Web Text)

Max Activating Token Index: 929

Text #3

Max Range: 4.6824. Min Range: -4.6824

Max Act: 4.4259. Min Act: -0.1700

Data Index: 7118001 (Open Web Text)

Max Activating Token Index: 661

Text #4

Max Range: 4.6824. Min Range: -4.6824

Max Act: 4.4277. Min Act: -0.1700

Data Index: 2892836 (Open Web Text)

Max Activating Token Index: 161

Text #5

Max Range: 4.6824. Min Range: -4.6824

Max Act: 4.4201. Min Act: -0.1700

Data Index: 325008 (Open Web Text)

Max Activating Token Index: 873

Text #6

Max Range: 4.6824. Min Range: -4.6824

Max Act: 4.3475. Min Act: -0.1700

Data Index: 6664059 (Open Web Text)

Max Activating Token Index: 895

Text #7

Max Range: 4.6824. Min Range: -4.6824

Max Act: 4.3243. Min Act: -0.1700

Data Index: 5518208 (Open Web Text)

Max Activating Token Index: 870

Text #8

Max Range: 4.6824. Min Range: -4.6824

Max Act: 4.3465. Min Act: -0.1700

Data Index: 5777925 (Open Web Text)

Max Activating Token Index: 108

Text #9

Max Range: 4.6824. Min Range: -4.6824

Max Act: 4.3531. Min Act: -0.1700

Data Index: 4374427 (Open Web Text)

Max Activating Token Index: 58

Text #10

Max Range: 4.6824. Min Range: -4.6824

Max Act: 4.3256. Min Act: -0.1700

Data Index: 6101803 (Open Web Text)

Max Activating Token Index: 691

Text #11

Max Range: 4.6824. Min Range: -4.6824

Max Act: 4.2947. Min Act: -0.1700

Data Index: 7068762 (Open Web Text)

Max Activating Token Index: 197

Text #12

Max Range: 4.6824. Min Range: -4.6824

Max Act: 4.3007. Min Act: -0.1700

Data Index: 3878686 (Open Web Text)

Max Activating Token Index: 797

Text #13

Max Range: 4.6824. Min Range: -4.6824

Max Act: 4.3172. Min Act: -0.1700

Data Index: 5829432 (Open Web Text)

Max Activating Token Index: 145

Text #14

Max Range: 4.6824. Min Range: -4.6824

Max Act: 4.3020. Min Act: -0.1700

Data Index: 2168866 (Open Web Text)

Max Activating Token Index: 225

Text #15

Max Range: 4.6824. Min Range: -4.6824

Max Act: 4.3198. Min Act: -0.1700

Data Index: 5374111 (Open Web Text)

Max Activating Token Index: 530

Text #16

Max Range: 4.6824. Min Range: -4.6824

Max Act: 4.3086. Min Act: -0.1700

Data Index: 1376062 (Open Web Text)

Max Activating Token Index: 454

Text #17

Max Range: 4.6824. Min Range: -4.6824

Max Act: 4.2728. Min Act: -0.1700

Data Index: 6583455 (Open Web Text)

Max Activating Token Index: 393

Text #18

Max Range: 4.6824. Min Range: -4.6824

Max Act: 4.2720. Min Act: -0.1700

Data Index: 262301 (Open Web Text)

Max Activating Token Index: 642

Text #19

Max Range: 4.6824. Min Range: -4.6824

Max Act: 4.2797. Min Act: -0.1700

Data Index: 3113812 (Open Web Text)

Max Activating Token Index: 57