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

Dataset: Open Web Text

Neuron 987 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: 4.6974. Min Range: -4.6974

Max Act: 4.6974. Min Act: -0.1700

Data Index: 7855015 (Open Web Text)

Max Activating Token Index: 523

Text #1

Max Range: 4.6974. Min Range: -4.6974

Max Act: 4.6698. Min Act: -0.1700

Data Index: 449141 (Open Web Text)

Max Activating Token Index: 440

Text #2

Max Range: 4.6974. Min Range: -4.6974

Max Act: 4.6163. Min Act: -0.1700

Data Index: 5223326 (Open Web Text)

Max Activating Token Index: 260

Text #3

Max Range: 4.6974. Min Range: -4.6974

Max Act: 4.6324. Min Act: -0.1700

Data Index: 6567308 (Open Web Text)

Max Activating Token Index: 944

Text #4

Max Range: 4.6974. Min Range: -4.6974

Max Act: 4.6099. Min Act: -0.1700

Data Index: 4217185 (Open Web Text)

Max Activating Token Index: 753

Text #5

Max Range: 4.6974. Min Range: -4.6974

Max Act: 4.5948. Min Act: -0.1700

Data Index: 6567309 (Open Web Text)

Max Activating Token Index: 183

Text #6

Max Range: 4.6974. Min Range: -4.6974

Max Act: 4.5919. Min Act: -0.1700

Data Index: 2523012 (Open Web Text)

Max Activating Token Index: 845

Text #7

Max Range: 4.6974. Min Range: -4.6974

Max Act: 4.5610. Min Act: -0.1700

Data Index: 5382838 (Open Web Text)

Max Activating Token Index: 126

Text #8

Max Range: 4.6974. Min Range: -4.6974

Max Act: 4.5879. Min Act: -0.1700

Data Index: 6510931 (Open Web Text)

Max Activating Token Index: 705

Text #9

Max Range: 4.6974. Min Range: -4.6974

Max Act: 4.5295. Min Act: -0.1700

Data Index: 7116616 (Open Web Text)

Max Activating Token Index: 460

Text #10

Max Range: 4.6974. Min Range: -4.6974

Max Act: 4.5379. Min Act: -0.1700

Data Index: 3045493 (Open Web Text)

Max Activating Token Index: 926

Text #11

Max Range: 4.6974. Min Range: -4.6974

Max Act: 4.5412. Min Act: -0.1700

Data Index: 1566348 (Open Web Text)

Max Activating Token Index: 573

Text #12

Max Range: 4.6974. Min Range: -4.6974

Max Act: 4.5368. Min Act: -0.1700

Data Index: 5271358 (Open Web Text)

Max Activating Token Index: 268

Text #13

Max Range: 4.6974. Min Range: -4.6974

Max Act: 4.5099. Min Act: -0.1700

Data Index: 3988413 (Open Web Text)

Max Activating Token Index: 518

Text #14

Max Range: 4.6974. Min Range: -4.6974

Max Act: 4.5158. Min Act: -0.1700

Data Index: 7177603 (Open Web Text)

Max Activating Token Index: 1008

Text #15

Max Range: 4.6974. Min Range: -4.6974

Max Act: 4.5150. Min Act: -0.1700

Data Index: 2962960 (Open Web Text)

Max Activating Token Index: 891

Text #16

Max Range: 4.6974. Min Range: -4.6974

Max Act: 4.5033. Min Act: -0.1700

Data Index: 7368669 (Open Web Text)

Max Activating Token Index: 263

Text #17

Max Range: 4.6974. Min Range: -4.6974

Max Act: 4.5084. Min Act: -0.1700

Data Index: 4368388 (Open Web Text)

Max Activating Token Index: 441

Text #18

Max Range: 4.6974. Min Range: -4.6974

Max Act: 4.5149. Min Act: -0.1700

Data Index: 3497722 (Open Web Text)

Max Activating Token Index: 108

Text #19

Max Range: 4.6974. Min Range: -4.6974

Max Act: 4.5138. Min Act: -0.1700

Data Index: 805447 (Open Web Text)

Max Activating Token Index: 737