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

Dataset: Open Web Text

Neuron 215 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: 3.5284. Min Range: -3.5284

Max Act: 3.5284. Min Act: -0.1700

Data Index: 8245123 (Open Web Text)

Max Activating Token Index: 276

Text #1

Max Range: 3.5284. Min Range: -3.5284

Max Act: 3.4840. Min Act: -0.1700

Data Index: 6877624 (Open Web Text)

Max Activating Token Index: 487

Text #2

Max Range: 3.5284. Min Range: -3.5284

Max Act: 3.4414. Min Act: -0.1700

Data Index: 1723656 (Open Web Text)

Max Activating Token Index: 684

Text #3

Max Range: 3.5284. Min Range: -3.5284

Max Act: 3.4530. Min Act: -0.1700

Data Index: 3271914 (Open Web Text)

Max Activating Token Index: 373

Text #4

Max Range: 3.5284. Min Range: -3.5284

Max Act: 3.4606. Min Act: -0.1700

Data Index: 2149464 (Open Web Text)

Max Activating Token Index: 526

Text #5

Max Range: 3.5284. Min Range: -3.5284

Max Act: 3.4182. Min Act: -0.1700

Data Index: 7891423 (Open Web Text)

Max Activating Token Index: 92

Text #6

Max Range: 3.5284. Min Range: -3.5284

Max Act: 3.4051. Min Act: -0.1700

Data Index: 1910524 (Open Web Text)

Max Activating Token Index: 912

Text #7

Max Range: 3.5284. Min Range: -3.5284

Max Act: 3.3893. Min Act: -0.1700

Data Index: 8579482 (Open Web Text)

Max Activating Token Index: 969

Text #8

Max Range: 3.5284. Min Range: -3.5284

Max Act: 3.3949. Min Act: -0.1700

Data Index: 7948420 (Open Web Text)

Max Activating Token Index: 923

Text #9

Max Range: 3.5284. Min Range: -3.5284

Max Act: 3.3676. Min Act: -0.1700

Data Index: 4088184 (Open Web Text)

Max Activating Token Index: 788

Text #10

Max Range: 3.5284. Min Range: -3.5284

Max Act: 3.3449. Min Act: -0.1700

Data Index: 7666350 (Open Web Text)

Max Activating Token Index: 900

Text #11

Max Range: 3.5284. Min Range: -3.5284

Max Act: 3.3599. Min Act: -0.1700

Data Index: 2352296 (Open Web Text)

Max Activating Token Index: 462

Text #12

Max Range: 3.5284. Min Range: -3.5284

Max Act: 3.3486. Min Act: -0.1700

Data Index: 5819337 (Open Web Text)

Max Activating Token Index: 574

Text #13

Max Range: 3.5284. Min Range: -3.5284

Max Act: 3.3447. Min Act: -0.1700

Data Index: 259799 (Open Web Text)

Max Activating Token Index: 748

Text #14

Max Range: 3.5284. Min Range: -3.5284

Max Act: 3.3292. Min Act: -0.1700

Data Index: 366140 (Open Web Text)

Max Activating Token Index: 583

Text #15

Max Range: 3.5284. Min Range: -3.5284

Max Act: 3.3349. Min Act: -0.1700

Data Index: 4355692 (Open Web Text)

Max Activating Token Index: 686

Text #16

Max Range: 3.5284. Min Range: -3.5284

Max Act: 3.3241. Min Act: -0.1700

Data Index: 8575288 (Open Web Text)

Max Activating Token Index: 216

Text #17

Max Range: 3.5284. Min Range: -3.5284

Max Act: 3.3167. Min Act: -0.1700

Data Index: 6369011 (Open Web Text)

Max Activating Token Index: 96

Text #18

Max Range: 3.5284. Min Range: -3.5284

Max Act: 3.2938. Min Act: -0.1700

Data Index: 1376516 (Open Web Text)

Max Activating Token Index: 237

Text #19

Max Range: 3.5284. Min Range: -3.5284

Max Act: 3.3198. Min Act: -0.1700

Data Index: 2588620 (Open Web Text)

Max Activating Token Index: 548