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

Dataset: Open Web Text

Neuron 707 in Layer 6

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: 4.8569. Min Range: -4.8569

Max Act: 4.8569. Min Act: -0.1700

Data Index: 8064529 (Open Web Text)

Max Activating Token Index: 817

Text #1

Max Range: 4.8569. Min Range: -4.8569

Max Act: 4.8142. Min Act: -0.1700

Data Index: 4060958 (Open Web Text)

Max Activating Token Index: 410

Text #2

Max Range: 4.8569. Min Range: -4.8569

Max Act: 4.7897. Min Act: -0.1700

Data Index: 3980487 (Open Web Text)

Max Activating Token Index: 200

Text #3

Max Range: 4.8569. Min Range: -4.8569

Max Act: 4.8057. Min Act: -0.1700

Data Index: 5743488 (Open Web Text)

Max Activating Token Index: 398

Text #4

Max Range: 4.8569. Min Range: -4.8569

Max Act: 4.7899. Min Act: -0.1700

Data Index: 5792135 (Open Web Text)

Max Activating Token Index: 331

Text #5

Max Range: 4.8569. Min Range: -4.8569

Max Act: 4.6985. Min Act: -0.1700

Data Index: 1540989 (Open Web Text)

Max Activating Token Index: 430

Text #6

Max Range: 4.8569. Min Range: -4.8569

Max Act: 4.8126. Min Act: -0.1700

Data Index: 8101022 (Open Web Text)

Max Activating Token Index: 690

Text #7

Max Range: 4.8569. Min Range: -4.8569

Max Act: 4.7392. Min Act: -0.1700

Data Index: 7255854 (Open Web Text)

Max Activating Token Index: 996

Text #8

Max Range: 4.8569. Min Range: -4.8569

Max Act: 4.6903. Min Act: -0.1700

Data Index: 4666198 (Open Web Text)

Max Activating Token Index: 345

Text #9

Max Range: 4.8569. Min Range: -4.8569

Max Act: 4.7382. Min Act: -0.1700

Data Index: 1617152 (Open Web Text)

Max Activating Token Index: 297

Text #10

Max Range: 4.8569. Min Range: -4.8569

Max Act: 4.7038. Min Act: -0.1700

Data Index: 315229 (Open Web Text)

Max Activating Token Index: 209

Text #11

Max Range: 4.8569. Min Range: -4.8569

Max Act: 4.7255. Min Act: -0.1700

Data Index: 196878 (Open Web Text)

Max Activating Token Index: 971

Text #12

Max Range: 4.8569. Min Range: -4.8569

Max Act: 4.6886. Min Act: -0.1700

Data Index: 4511208 (Open Web Text)

Max Activating Token Index: 916

Text #13

Max Range: 4.8569. Min Range: -4.8569

Max Act: 4.7036. Min Act: -0.1700

Data Index: 5899001 (Open Web Text)

Max Activating Token Index: 257

Text #14

Max Range: 4.8569. Min Range: -4.8569

Max Act: 4.6857. Min Act: -0.1700

Data Index: 4561572 (Open Web Text)

Max Activating Token Index: 163

Text #15

Max Range: 4.8569. Min Range: -4.8569

Max Act: 4.7310. Min Act: -0.1700

Data Index: 2486299 (Open Web Text)

Max Activating Token Index: 698

Text #16

Max Range: 4.8569. Min Range: -4.8569

Max Act: 4.7050. Min Act: -0.1700

Data Index: 5306580 (Open Web Text)

Max Activating Token Index: 564

Text #17

Max Range: 4.8569. Min Range: -4.8569

Max Act: 4.7081. Min Act: -0.1700

Data Index: 4917312 (Open Web Text)

Max Activating Token Index: 94

Text #18

Max Range: 4.8569. Min Range: -4.8569

Max Act: 4.6981. Min Act: -0.1700

Data Index: 2963338 (Open Web Text)

Max Activating Token Index: 277

Text #19

Max Range: 4.8569. Min Range: -4.8569

Max Act: 4.6951. Min Act: -0.1700

Data Index: 4419447 (Open Web Text)

Max Activating Token Index: 287