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

Dataset: Open Web Text

Neuron 387 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: 3.3020. Min Range: -3.3020

Max Act: 3.3020. Min Act: -0.1700

Data Index: 1196978 (Open Web Text)

Max Activating Token Index: 971

Text #1

Max Range: 3.3020. Min Range: -3.3020

Max Act: 3.1304. Min Act: -0.1700

Data Index: 8245608 (Open Web Text)

Max Activating Token Index: 692

Text #2

Max Range: 3.3020. Min Range: -3.3020

Max Act: 3.1435. Min Act: -0.1700

Data Index: 6766381 (Open Web Text)

Max Activating Token Index: 23

Text #3

Max Range: 3.3020. Min Range: -3.3020

Max Act: 3.1612. Min Act: -0.1700

Data Index: 7046206 (Open Web Text)

Max Activating Token Index: 927

Text #4

Max Range: 3.3020. Min Range: -3.3020

Max Act: 3.1026. Min Act: -0.1700

Data Index: 3479645 (Open Web Text)

Max Activating Token Index: 18

Text #5

Max Range: 3.3020. Min Range: -3.3020

Max Act: 3.0284. Min Act: -0.1700

Data Index: 4876795 (Open Web Text)

Max Activating Token Index: 340

Text #6

Max Range: 3.3020. Min Range: -3.3020

Max Act: 2.9620. Min Act: -0.1700

Data Index: 4301495 (Open Web Text)

Max Activating Token Index: 799

Text #7

Max Range: 3.3020. Min Range: -3.3020

Max Act: 3.0276. Min Act: -0.1700

Data Index: 5475442 (Open Web Text)

Max Activating Token Index: 141

Text #8

Max Range: 3.3020. Min Range: -3.3020

Max Act: 2.9678. Min Act: -0.1700

Data Index: 3977537 (Open Web Text)

Max Activating Token Index: 603

Text #9

Max Range: 3.3020. Min Range: -3.3020

Max Act: 2.9438. Min Act: -0.1700

Data Index: 7043781 (Open Web Text)

Max Activating Token Index: 1012

Text #10

Max Range: 3.3020. Min Range: -3.3020

Max Act: 2.9108. Min Act: -0.1700

Data Index: 5148820 (Open Web Text)

Max Activating Token Index: 465

Text #11

Max Range: 3.3020. Min Range: -3.3020

Max Act: 2.9054. Min Act: -0.1700

Data Index: 2429364 (Open Web Text)

Max Activating Token Index: 471

Text #12

Max Range: 3.3020. Min Range: -3.3020

Max Act: 2.9017. Min Act: -0.1700

Data Index: 998296 (Open Web Text)

Max Activating Token Index: 528

Text #13

Max Range: 3.3020. Min Range: -3.3020

Max Act: 2.8673. Min Act: -0.1700

Data Index: 8360657 (Open Web Text)

Max Activating Token Index: 705

Text #14

Max Range: 3.3020. Min Range: -3.3020

Max Act: 2.9285. Min Act: -0.1700

Data Index: 3750645 (Open Web Text)

Max Activating Token Index: 597

Text #15

Max Range: 3.3020. Min Range: -3.3020

Max Act: 2.8597. Min Act: -0.1700

Data Index: 1092444 (Open Web Text)

Max Activating Token Index: 243

Text #16

Max Range: 3.3020. Min Range: -3.3020

Max Act: 2.8499. Min Act: -0.1700

Data Index: 5188683 (Open Web Text)

Max Activating Token Index: 211

Text #17

Max Range: 3.3020. Min Range: -3.3020

Max Act: 2.8156. Min Act: -0.1700

Data Index: 7003418 (Open Web Text)

Max Activating Token Index: 987

Text #18

Max Range: 3.3020. Min Range: -3.3020

Max Act: 2.7938. Min Act: -0.1700

Data Index: 8093239 (Open Web Text)

Max Activating Token Index: 72

Text #19

Max Range: 3.3020. Min Range: -3.3020

Max Act: 2.7694. Min Act: -0.1700

Data Index: 4557068 (Open Web Text)

Max Activating Token Index: 303