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

Dataset: Open Web Text

Neuron 1926 in Layer 4

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: 4.7787. Min Range: -4.7787

Max Act: 4.7418. Min Act: -0.1700

Data Index: 7230775 (Open Web Text)

Max Activating Token Index: 615

Text #1

Max Range: 4.7787. Min Range: -4.7787

Max Act: 4.7699. Min Act: -0.1700

Data Index: 6903745 (Open Web Text)

Max Activating Token Index: 845

Text #2

Max Range: 4.7787. Min Range: -4.7787

Max Act: 4.7564. Min Act: -0.1700

Data Index: 1412781 (Open Web Text)

Max Activating Token Index: 359

Text #3

Max Range: 4.7787. Min Range: -4.7787

Max Act: 4.7372. Min Act: -0.1700

Data Index: 1180710 (Open Web Text)

Max Activating Token Index: 448

Text #4

Max Range: 4.7787. Min Range: -4.7787

Max Act: 4.7787. Min Act: -0.1700

Data Index: 8050730 (Open Web Text)

Max Activating Token Index: 628

Text #5

Max Range: 4.7787. Min Range: -4.7787

Max Act: 4.6771. Min Act: -0.1700

Data Index: 6182001 (Open Web Text)

Max Activating Token Index: 234

Text #6

Max Range: 4.7787. Min Range: -4.7787

Max Act: 4.6655. Min Act: -0.1700

Data Index: 4607099 (Open Web Text)

Max Activating Token Index: 137

Text #7

Max Range: 4.7787. Min Range: -4.7787

Max Act: 4.6437. Min Act: -0.1700

Data Index: 4194018 (Open Web Text)

Max Activating Token Index: 1006

Text #8

Max Range: 4.7787. Min Range: -4.7787

Max Act: 4.6296. Min Act: -0.1700

Data Index: 2130384 (Open Web Text)

Max Activating Token Index: 289

Text #9

Max Range: 4.7787. Min Range: -4.7787

Max Act: 4.6588. Min Act: -0.1700

Data Index: 1630646 (Open Web Text)

Max Activating Token Index: 856

Text #10

Max Range: 4.7787. Min Range: -4.7787

Max Act: 4.5782. Min Act: -0.1700

Data Index: 5117338 (Open Web Text)

Max Activating Token Index: 61

Text #11

Max Range: 4.7787. Min Range: -4.7787

Max Act: 4.5952. Min Act: -0.1700

Data Index: 5404615 (Open Web Text)

Max Activating Token Index: 921

Text #12

Max Range: 4.7787. Min Range: -4.7787

Max Act: 4.6235. Min Act: -0.1700

Data Index: 2128385 (Open Web Text)

Max Activating Token Index: 466

Text #13

Max Range: 4.7787. Min Range: -4.7787

Max Act: 4.5978. Min Act: -0.1700

Data Index: 5614972 (Open Web Text)

Max Activating Token Index: 640

Text #14

Max Range: 4.7787. Min Range: -4.7787

Max Act: 4.5635. Min Act: -0.1700

Data Index: 2992391 (Open Web Text)

Max Activating Token Index: 577

Text #15

Max Range: 4.7787. Min Range: -4.7787

Max Act: 4.5845. Min Act: -0.1700

Data Index: 3852687 (Open Web Text)

Max Activating Token Index: 737

Text #16

Max Range: 4.7787. Min Range: -4.7787

Max Act: 4.5973. Min Act: -0.1700

Data Index: 4015221 (Open Web Text)

Max Activating Token Index: 266

Text #17

Max Range: 4.7787. Min Range: -4.7787

Max Act: 4.5961. Min Act: -0.1700

Data Index: 6899015 (Open Web Text)

Max Activating Token Index: 815

Text #18

Max Range: 4.7787. Min Range: -4.7787

Max Act: 4.5984. Min Act: -0.1700

Data Index: 7842705 (Open Web Text)

Max Activating Token Index: 355

Text #19

Max Range: 4.7787. Min Range: -4.7787

Max Act: 4.5889. Min Act: -0.1700

Data Index: 1286782 (Open Web Text)

Max Activating Token Index: 554