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

Dataset: Open Web Text

Neuron 3 in Layer 2

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: 5.0959. Min Range: -5.0959

Max Act: 5.0956. Min Act: -0.1700

Data Index: 4348519 (Open Web Text)

Max Activating Token Index: 89

Text #1

Max Range: 5.0959. Min Range: -5.0959

Max Act: 5.0902. Min Act: -0.1700

Data Index: 4536446 (Open Web Text)

Max Activating Token Index: 201

Text #2

Max Range: 5.0959. Min Range: -5.0959

Max Act: 5.0959. Min Act: -0.1700

Data Index: 3252417 (Open Web Text)

Max Activating Token Index: 236

Text #3

Max Range: 5.0959. Min Range: -5.0959

Max Act: 5.0490. Min Act: -0.1700

Data Index: 2913869 (Open Web Text)

Max Activating Token Index: 39

Text #4

Max Range: 5.0959. Min Range: -5.0959

Max Act: 5.0802. Min Act: -0.1700

Data Index: 8236359 (Open Web Text)

Max Activating Token Index: 236

Text #5

Max Range: 5.0959. Min Range: -5.0959

Max Act: 5.0223. Min Act: -0.1700

Data Index: 2735191 (Open Web Text)

Max Activating Token Index: 28

Text #6

Max Range: 5.0959. Min Range: -5.0959

Max Act: 5.0106. Min Act: -0.1700

Data Index: 1599387 (Open Web Text)

Max Activating Token Index: 13

Text #7

Max Range: 5.0959. Min Range: -5.0959

Max Act: 5.0268. Min Act: -0.1700

Data Index: 3026127 (Open Web Text)

Max Activating Token Index: 628

Text #8

Max Range: 5.0959. Min Range: -5.0959

Max Act: 5.0290. Min Act: -0.1700

Data Index: 4806960 (Open Web Text)

Max Activating Token Index: 260

Text #9

Max Range: 5.0959. Min Range: -5.0959

Max Act: 5.0409. Min Act: -0.1700

Data Index: 4126462 (Open Web Text)

Max Activating Token Index: 437

Text #10

Max Range: 5.0959. Min Range: -5.0959

Max Act: 4.9935. Min Act: -0.1700

Data Index: 83729 (Open Web Text)

Max Activating Token Index: 542

Text #11

Max Range: 5.0959. Min Range: -5.0959

Max Act: 5.0101. Min Act: -0.1700

Data Index: 7598451 (Open Web Text)

Max Activating Token Index: 939

Text #12

Max Range: 5.0959. Min Range: -5.0959

Max Act: 5.0089. Min Act: -0.1700

Data Index: 1708156 (Open Web Text)

Max Activating Token Index: 739

Text #13

Max Range: 5.0959. Min Range: -5.0959

Max Act: 4.9688. Min Act: -0.1700

Data Index: 5886307 (Open Web Text)

Max Activating Token Index: 253

Text #14

Max Range: 5.0959. Min Range: -5.0959

Max Act: 4.9616. Min Act: -0.1700

Data Index: 5082528 (Open Web Text)

Max Activating Token Index: 21

Text #15

Max Range: 5.0959. Min Range: -5.0959

Max Act: 4.9570. Min Act: -0.1700

Data Index: 2283136 (Open Web Text)

Max Activating Token Index: 13

Text #16

Max Range: 5.0959. Min Range: -5.0959

Max Act: 4.9660. Min Act: -0.1700

Data Index: 161170 (Open Web Text)

Max Activating Token Index: 39

Text #17

Max Range: 5.0959. Min Range: -5.0959

Max Act: 4.9573. Min Act: -0.1700

Data Index: 5769351 (Open Web Text)

Max Activating Token Index: 149

Text #18

Max Range: 5.0959. Min Range: -5.0959

Max Act: 4.9634. Min Act: -0.1700

Data Index: 1454972 (Open Web Text)

Max Activating Token Index: 192

Text #19

Max Range: 5.0959. Min Range: -5.0959

Max Act: 4.9223. Min Act: -0.1700

Data Index: 4262006 (Open Web Text)

Max Activating Token Index: 1008