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

Dataset: Open Web Text

Neuron 2427 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: 4.0897. Min Range: -4.0897

Max Act: 4.0897. Min Act: -0.1700

Data Index: 6352000 (Open Web Text)

Max Activating Token Index: 668

Text #1

Max Range: 4.0897. Min Range: -4.0897

Max Act: 3.9017. Min Act: -0.1700

Data Index: 6884779 (Open Web Text)

Max Activating Token Index: 413

Text #2

Max Range: 4.0897. Min Range: -4.0897

Max Act: 3.8723. Min Act: -0.1700

Data Index: 5915909 (Open Web Text)

Max Activating Token Index: 720

Text #3

Max Range: 4.0897. Min Range: -4.0897

Max Act: 3.7923. Min Act: -0.1700

Data Index: 4022293 (Open Web Text)

Max Activating Token Index: 687

Text #4

Max Range: 4.0897. Min Range: -4.0897

Max Act: 3.8105. Min Act: -0.1700

Data Index: 4767203 (Open Web Text)

Max Activating Token Index: 205

Text #5

Max Range: 4.0897. Min Range: -4.0897

Max Act: 3.7428. Min Act: -0.1700

Data Index: 6777361 (Open Web Text)

Max Activating Token Index: 489

Text #6

Max Range: 4.0897. Min Range: -4.0897

Max Act: 3.7314. Min Act: -0.1700

Data Index: 1939016 (Open Web Text)

Max Activating Token Index: 467

Text #7

Max Range: 4.0897. Min Range: -4.0897

Max Act: 3.6734. Min Act: -0.1700

Data Index: 3714707 (Open Web Text)

Max Activating Token Index: 257

Text #8

Max Range: 4.0897. Min Range: -4.0897

Max Act: 3.6939. Min Act: -0.1700

Data Index: 342630 (Open Web Text)

Max Activating Token Index: 218

Text #9

Max Range: 4.0897. Min Range: -4.0897

Max Act: 3.7316. Min Act: -0.1700

Data Index: 1086242 (Open Web Text)

Max Activating Token Index: 524

Text #10

Max Range: 4.0897. Min Range: -4.0897

Max Act: 3.6086. Min Act: -0.1700

Data Index: 5348894 (Open Web Text)

Max Activating Token Index: 578

Text #11

Max Range: 4.0897. Min Range: -4.0897

Max Act: 3.6434. Min Act: -0.1700

Data Index: 6290335 (Open Web Text)

Max Activating Token Index: 169

Text #12

Max Range: 4.0897. Min Range: -4.0897

Max Act: 3.5680. Min Act: -0.1700

Data Index: 6190491 (Open Web Text)

Max Activating Token Index: 248

Text #13

Max Range: 4.0897. Min Range: -4.0897

Max Act: 3.5802. Min Act: -0.1700

Data Index: 1694239 (Open Web Text)

Max Activating Token Index: 134

Text #14

Max Range: 4.0897. Min Range: -4.0897

Max Act: 3.5384. Min Act: -0.1700

Data Index: 5947775 (Open Web Text)

Max Activating Token Index: 401

Text #15

Max Range: 4.0897. Min Range: -4.0897

Max Act: 3.5687. Min Act: -0.1700

Data Index: 8611001 (Open Web Text)

Max Activating Token Index: 195

Text #16

Max Range: 4.0897. Min Range: -4.0897

Max Act: 3.5562. Min Act: -0.1700

Data Index: 8267876 (Open Web Text)

Max Activating Token Index: 898

Text #17

Max Range: 4.0897. Min Range: -4.0897

Max Act: 3.5854. Min Act: -0.1700

Data Index: 4351367 (Open Web Text)

Max Activating Token Index: 729

Text #18

Max Range: 4.0897. Min Range: -4.0897

Max Act: 3.5528. Min Act: -0.1700

Data Index: 1262678 (Open Web Text)

Max Activating Token Index: 446

Text #19

Max Range: 4.0897. Min Range: -4.0897

Max Act: 3.5534. Min Act: -0.1700

Data Index: 3917021 (Open Web Text)

Max Activating Token Index: 965