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

Dataset: Open Web Text

Neuron 437 in Layer 0

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: 4.5117. Min Range: -4.5117

Max Act: 4.5117. Min Act: -0.1700

Data Index: 7290138 (Open Web Text)

Max Activating Token Index: 285

Text #1

Max Range: 4.5117. Min Range: -4.5117

Max Act: 4.4964. Min Act: -0.1700

Data Index: 847381 (Open Web Text)

Max Activating Token Index: 289

Text #2

Max Range: 4.5117. Min Range: -4.5117

Max Act: 4.4772. Min Act: -0.1700

Data Index: 3470372 (Open Web Text)

Max Activating Token Index: 1014

Text #3

Max Range: 4.5117. Min Range: -4.5117

Max Act: 4.4696. Min Act: -0.1700

Data Index: 5667806 (Open Web Text)

Max Activating Token Index: 94

Text #4

Max Range: 4.5117. Min Range: -4.5117

Max Act: 4.4181. Min Act: -0.1700

Data Index: 1478796 (Open Web Text)

Max Activating Token Index: 295

Text #5

Max Range: 4.5117. Min Range: -4.5117

Max Act: 4.3703. Min Act: -0.1700

Data Index: 4598211 (Open Web Text)

Max Activating Token Index: 752

Text #6

Max Range: 4.5117. Min Range: -4.5117

Max Act: 4.4070. Min Act: -0.1700

Data Index: 1676384 (Open Web Text)

Max Activating Token Index: 10

Text #7

Max Range: 4.5117. Min Range: -4.5117

Max Act: 4.3788. Min Act: -0.1700

Data Index: 8294150 (Open Web Text)

Max Activating Token Index: 14

Text #8

Max Range: 4.5117. Min Range: -4.5117

Max Act: 4.3793. Min Act: -0.1700

Data Index: 2658861 (Open Web Text)

Max Activating Token Index: 714

Text #9

Max Range: 4.5117. Min Range: -4.5117

Max Act: 4.3774. Min Act: -0.1700

Data Index: 5820263 (Open Web Text)

Max Activating Token Index: 825

Text #10

Max Range: 4.5117. Min Range: -4.5117

Max Act: 4.3925. Min Act: -0.1700

Data Index: 5783039 (Open Web Text)

Max Activating Token Index: 370

Text #11

Max Range: 4.5117. Min Range: -4.5117

Max Act: 4.3959. Min Act: -0.1700

Data Index: 4766183 (Open Web Text)

Max Activating Token Index: 739

Text #12

Max Range: 4.5117. Min Range: -4.5117

Max Act: 4.3536. Min Act: -0.1700

Data Index: 3302667 (Open Web Text)

Max Activating Token Index: 697

Text #13

Max Range: 4.5117. Min Range: -4.5117

Max Act: 4.3526. Min Act: -0.1700

Data Index: 6060969 (Open Web Text)

Max Activating Token Index: 215

Text #14

Max Range: 4.5117. Min Range: -4.5117

Max Act: 4.3644. Min Act: -0.1700

Data Index: 2346307 (Open Web Text)

Max Activating Token Index: 387

Text #15

Max Range: 4.5117. Min Range: -4.5117

Max Act: 4.3530. Min Act: -0.1700

Data Index: 675002 (Open Web Text)

Max Activating Token Index: 14

Text #16

Max Range: 4.5117. Min Range: -4.5117

Max Act: 4.3612. Min Act: -0.1700

Data Index: 5412679 (Open Web Text)

Max Activating Token Index: 780

Text #17

Max Range: 4.5117. Min Range: -4.5117

Max Act: 4.3737. Min Act: -0.1700

Data Index: 1945884 (Open Web Text)

Max Activating Token Index: 698

Text #18

Max Range: 4.5117. Min Range: -4.5117

Max Act: 4.3765. Min Act: -0.1700

Data Index: 8763015 (Open Web Text)

Max Activating Token Index: 394

Text #19

Max Range: 4.5117. Min Range: -4.5117

Max Act: 4.3196. Min Act: -0.1700

Data Index: 4589557 (Open Web Text)

Max Activating Token Index: 865