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

Dataset: Open Web Text

Neuron 3007 in Layer 1

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: 4.6017. Min Range: -4.6017

Max Act: 4.6017. Min Act: -0.1700

Data Index: 1262104 (Open Web Text)

Max Activating Token Index: 483

Text #1

Max Range: 4.6017. Min Range: -4.6017

Max Act: 4.5769. Min Act: -0.1700

Data Index: 5935238 (Open Web Text)

Max Activating Token Index: 599

Text #2

Max Range: 4.6017. Min Range: -4.6017

Max Act: 4.5500. Min Act: -0.1700

Data Index: 3799035 (Open Web Text)

Max Activating Token Index: 178

Text #3

Max Range: 4.6017. Min Range: -4.6017

Max Act: 4.5601. Min Act: -0.1700

Data Index: 5395471 (Open Web Text)

Max Activating Token Index: 560

Text #4

Max Range: 4.6017. Min Range: -4.6017

Max Act: 4.5341. Min Act: -0.1700

Data Index: 4572628 (Open Web Text)

Max Activating Token Index: 713

Text #5

Max Range: 4.6017. Min Range: -4.6017

Max Act: 4.5542. Min Act: -0.1700

Data Index: 559923 (Open Web Text)

Max Activating Token Index: 483

Text #6

Max Range: 4.6017. Min Range: -4.6017

Max Act: 4.5319. Min Act: -0.1700

Data Index: 5440673 (Open Web Text)

Max Activating Token Index: 258

Text #7

Max Range: 4.6017. Min Range: -4.6017

Max Act: 4.5630. Min Act: -0.1700

Data Index: 3370429 (Open Web Text)

Max Activating Token Index: 432

Text #8

Max Range: 4.6017. Min Range: -4.6017

Max Act: 4.5505. Min Act: -0.1700

Data Index: 3156552 (Open Web Text)

Max Activating Token Index: 663

Text #9

Max Range: 4.6017. Min Range: -4.6017

Max Act: 4.5204. Min Act: -0.1700

Data Index: 6748706 (Open Web Text)

Max Activating Token Index: 765

Text #10

Max Range: 4.6017. Min Range: -4.6017

Max Act: 4.5138. Min Act: -0.1700

Data Index: 7241983 (Open Web Text)

Max Activating Token Index: 178

Text #11

Max Range: 4.6017. Min Range: -4.6017

Max Act: 4.5230. Min Act: -0.1700

Data Index: 687741 (Open Web Text)

Max Activating Token Index: 388

Text #12

Max Range: 4.6017. Min Range: -4.6017

Max Act: 4.4941. Min Act: -0.1700

Data Index: 2342712 (Open Web Text)

Max Activating Token Index: 221

Text #13

Max Range: 4.6017. Min Range: -4.6017

Max Act: 4.5040. Min Act: -0.1700

Data Index: 8554187 (Open Web Text)

Max Activating Token Index: 308

Text #14

Max Range: 4.6017. Min Range: -4.6017

Max Act: 4.4779. Min Act: -0.1700

Data Index: 6067989 (Open Web Text)

Max Activating Token Index: 585

Text #15

Max Range: 4.6017. Min Range: -4.6017

Max Act: 4.4778. Min Act: -0.1700

Data Index: 8293119 (Open Web Text)

Max Activating Token Index: 489

Text #16

Max Range: 4.6017. Min Range: -4.6017

Max Act: 4.4541. Min Act: -0.1700

Data Index: 978640 (Open Web Text)

Max Activating Token Index: 533

Text #17

Max Range: 4.6017. Min Range: -4.6017

Max Act: 4.4325. Min Act: -0.1700

Data Index: 1975781 (Open Web Text)

Max Activating Token Index: 545

Text #18

Max Range: 4.6017. Min Range: -4.6017

Max Act: 4.4574. Min Act: -0.1700

Data Index: 898249 (Open Web Text)

Max Activating Token Index: 745

Text #19

Max Range: 4.6017. Min Range: -4.6017

Max Act: 4.4492. Min Act: -0.1700

Data Index: 4764143 (Open Web Text)

Max Activating Token Index: 592