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

Dataset: Open Web Text

Neuron 2724 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: 5.0198. Min Range: -5.0198

Max Act: 5.0198. Min Act: -0.1700

Data Index: 2072641 (Open Web Text)

Max Activating Token Index: 864

Text #1

Max Range: 5.0198. Min Range: -5.0198

Max Act: 4.8275. Min Act: -0.1700

Data Index: 607772 (Open Web Text)

Max Activating Token Index: 353

Text #2

Max Range: 5.0198. Min Range: -5.0198

Max Act: 4.6730. Min Act: -0.1700

Data Index: 531643 (Open Web Text)

Max Activating Token Index: 829

Text #3

Max Range: 5.0198. Min Range: -5.0198

Max Act: 4.6650. Min Act: -0.1700

Data Index: 2452241 (Open Web Text)

Max Activating Token Index: 768

Text #4

Max Range: 5.0198. Min Range: -5.0198

Max Act: 4.6099. Min Act: -0.1700

Data Index: 5119724 (Open Web Text)

Max Activating Token Index: 946

Text #5

Max Range: 5.0198. Min Range: -5.0198

Max Act: 4.5971. Min Act: -0.1700

Data Index: 4364409 (Open Web Text)

Max Activating Token Index: 484

Text #6

Max Range: 5.0198. Min Range: -5.0198

Max Act: 4.6266. Min Act: -0.1700

Data Index: 4016850 (Open Web Text)

Max Activating Token Index: 927

Text #7

Max Range: 5.0198. Min Range: -5.0198

Max Act: 4.6253. Min Act: -0.1700

Data Index: 3345950 (Open Web Text)

Max Activating Token Index: 129

Text #8

Max Range: 5.0198. Min Range: -5.0198

Max Act: 4.6050. Min Act: -0.1700

Data Index: 531641 (Open Web Text)

Max Activating Token Index: 576

Text #9

Max Range: 5.0198. Min Range: -5.0198

Max Act: 4.5798. Min Act: -0.1700

Data Index: 3345952 (Open Web Text)

Max Activating Token Index: 809

Text #10

Max Range: 5.0198. Min Range: -5.0198

Max Act: 4.5431. Min Act: -0.1700

Data Index: 5283556 (Open Web Text)

Max Activating Token Index: 264

Text #11

Max Range: 5.0198. Min Range: -5.0198

Max Act: 4.5285. Min Act: -0.1700

Data Index: 3609049 (Open Web Text)

Max Activating Token Index: 185

Text #12

Max Range: 5.0198. Min Range: -5.0198

Max Act: 4.5069. Min Act: -0.1700

Data Index: 3719766 (Open Web Text)

Max Activating Token Index: 441

Text #13

Max Range: 5.0198. Min Range: -5.0198

Max Act: 4.4815. Min Act: -0.1700

Data Index: 4701155 (Open Web Text)

Max Activating Token Index: 907

Text #14

Max Range: 5.0198. Min Range: -5.0198

Max Act: 4.5356. Min Act: -0.1700

Data Index: 7304393 (Open Web Text)

Max Activating Token Index: 489

Text #15

Max Range: 5.0198. Min Range: -5.0198

Max Act: 4.4753. Min Act: -0.1700

Data Index: 7767172 (Open Web Text)

Max Activating Token Index: 872

Text #16

Max Range: 5.0198. Min Range: -5.0198

Max Act: 4.4636. Min Act: -0.1700

Data Index: 2396673 (Open Web Text)

Max Activating Token Index: 454

Text #17

Max Range: 5.0198. Min Range: -5.0198

Max Act: 4.3994. Min Act: -0.1700

Data Index: 2576494 (Open Web Text)

Max Activating Token Index: 730

Text #18

Max Range: 5.0198. Min Range: -5.0198

Max Act: 4.4577. Min Act: -0.1700

Data Index: 6879617 (Open Web Text)

Max Activating Token Index: 311

Text #19

Max Range: 5.0198. Min Range: -5.0198

Max Act: 4.4142. Min Act: -0.1700

Data Index: 4577847 (Open Web Text)

Max Activating Token Index: 770