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

Dataset: Open Web Text

Neuron 679 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: 3.2627. Min Range: -3.2627

Max Act: 3.2627. Min Act: -0.1700

Data Index: 2039414 (Open Web Text)

Max Activating Token Index: 148

Text #1

Max Range: 3.2627. Min Range: -3.2627

Max Act: 3.2501. Min Act: -0.1700

Data Index: 194448 (Open Web Text)

Max Activating Token Index: 209

Text #2

Max Range: 3.2627. Min Range: -3.2627

Max Act: 3.1971. Min Act: -0.1700

Data Index: 8562027 (Open Web Text)

Max Activating Token Index: 723

Text #3

Max Range: 3.2627. Min Range: -3.2627

Max Act: 3.1882. Min Act: -0.1700

Data Index: 824791 (Open Web Text)

Max Activating Token Index: 974

Text #4

Max Range: 3.2627. Min Range: -3.2627

Max Act: 3.1630. Min Act: -0.1700

Data Index: 4160997 (Open Web Text)

Max Activating Token Index: 38

Text #5

Max Range: 3.2627. Min Range: -3.2627

Max Act: 3.0896. Min Act: -0.1700

Data Index: 6304922 (Open Web Text)

Max Activating Token Index: 348

Text #6

Max Range: 3.2627. Min Range: -3.2627

Max Act: 3.0898. Min Act: -0.1700

Data Index: 7423167 (Open Web Text)

Max Activating Token Index: 761

Text #7

Max Range: 3.2627. Min Range: -3.2627

Max Act: 3.0461. Min Act: -0.1700

Data Index: 571181 (Open Web Text)

Max Activating Token Index: 649

Text #8

Max Range: 3.2627. Min Range: -3.2627

Max Act: 3.0368. Min Act: -0.1700

Data Index: 5400761 (Open Web Text)

Max Activating Token Index: 267

Text #9

Max Range: 3.2627. Min Range: -3.2627

Max Act: 3.0455. Min Act: -0.1700

Data Index: 7788170 (Open Web Text)

Max Activating Token Index: 485

Text #10

Max Range: 3.2627. Min Range: -3.2627

Max Act: 3.0386. Min Act: -0.1700

Data Index: 3954193 (Open Web Text)

Max Activating Token Index: 13

Text #11

Max Range: 3.2627. Min Range: -3.2627

Max Act: 3.0143. Min Act: -0.1700

Data Index: 6487096 (Open Web Text)

Max Activating Token Index: 207

Text #12

Max Range: 3.2627. Min Range: -3.2627

Max Act: 2.9876. Min Act: -0.1700

Data Index: 3040141 (Open Web Text)

Max Activating Token Index: 181

Text #13

Max Range: 3.2627. Min Range: -3.2627

Max Act: 2.9881. Min Act: -0.1700

Data Index: 4295950 (Open Web Text)

Max Activating Token Index: 121

Text #14

Max Range: 3.2627. Min Range: -3.2627

Max Act: 3.0248. Min Act: -0.1700

Data Index: 390225 (Open Web Text)

Max Activating Token Index: 449

Text #15

Max Range: 3.2627. Min Range: -3.2627

Max Act: 2.9828. Min Act: -0.1700

Data Index: 8771346 (Open Web Text)

Max Activating Token Index: 705

Text #16

Max Range: 3.2627. Min Range: -3.2627

Max Act: 2.9770. Min Act: -0.1700

Data Index: 2601558 (Open Web Text)

Max Activating Token Index: 113

Text #17

Max Range: 3.2627. Min Range: -3.2627

Max Act: 2.9538. Min Act: -0.1700

Data Index: 4404328 (Open Web Text)

Max Activating Token Index: 600

Text #18

Max Range: 3.2627. Min Range: -3.2627

Max Act: 2.9738. Min Act: -0.1700

Data Index: 5781662 (Open Web Text)

Max Activating Token Index: 92

Text #19

Max Range: 3.2627. Min Range: -3.2627

Max Act: 2.9864. Min Act: -0.1700

Data Index: 1942664 (Open Web Text)

Max Activating Token Index: 290