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

Dataset: Open Web Text

Neuron 2750 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: 1.9735. Min Range: -1.9735

Max Act: 1.9735. Min Act: -0.1700

Data Index: 1588017 (Open Web Text)

Max Activating Token Index: 168

Text #1

Max Range: 1.9735. Min Range: -1.9735

Max Act: 1.9696. Min Act: -0.1700

Data Index: 7629086 (Open Web Text)

Max Activating Token Index: 53

Text #2

Max Range: 1.9735. Min Range: -1.9735

Max Act: 1.9527. Min Act: -0.1700

Data Index: 1554736 (Open Web Text)

Max Activating Token Index: 626

Text #3

Max Range: 1.9735. Min Range: -1.9735

Max Act: 1.9369. Min Act: -0.1700

Data Index: 1269949 (Open Web Text)

Max Activating Token Index: 11

Text #4

Max Range: 1.9735. Min Range: -1.9735

Max Act: 1.8998. Min Act: -0.1700

Data Index: 4056217 (Open Web Text)

Max Activating Token Index: 628

Text #5

Max Range: 1.9735. Min Range: -1.9735

Max Act: 1.8870. Min Act: -0.1700

Data Index: 6986245 (Open Web Text)

Max Activating Token Index: 447

Text #6

Max Range: 1.9735. Min Range: -1.9735

Max Act: 1.8961. Min Act: -0.1700

Data Index: 4250895 (Open Web Text)

Max Activating Token Index: 635

Text #7

Max Range: 1.9735. Min Range: -1.9735

Max Act: 1.8632. Min Act: -0.1700

Data Index: 1816621 (Open Web Text)

Max Activating Token Index: 468

Text #8

Max Range: 1.9735. Min Range: -1.9735

Max Act: 1.8649. Min Act: -0.1700

Data Index: 3923624 (Open Web Text)

Max Activating Token Index: 667

Text #9

Max Range: 1.9735. Min Range: -1.9735

Max Act: 1.8414. Min Act: -0.1700

Data Index: 7707314 (Open Web Text)

Max Activating Token Index: 658

Text #10

Max Range: 1.9735. Min Range: -1.9735

Max Act: 1.8558. Min Act: -0.1700

Data Index: 1672096 (Open Web Text)

Max Activating Token Index: 400

Text #11

Max Range: 1.9735. Min Range: -1.9735

Max Act: 1.8472. Min Act: -0.1699

Data Index: 7937768 (Open Web Text)

Max Activating Token Index: 70

Text #12

Max Range: 1.9735. Min Range: -1.9735

Max Act: 1.8474. Min Act: -0.1700

Data Index: 750739 (Open Web Text)

Max Activating Token Index: 574

Text #13

Max Range: 1.9735. Min Range: -1.9735

Max Act: 1.8435. Min Act: -0.1700

Data Index: 5217953 (Open Web Text)

Max Activating Token Index: 60

Text #14

Max Range: 1.9735. Min Range: -1.9735

Max Act: 1.8220. Min Act: -0.1700

Data Index: 7724655 (Open Web Text)

Max Activating Token Index: 132

Text #15

Max Range: 1.9735. Min Range: -1.9735

Max Act: 1.8428. Min Act: -0.1700

Data Index: 638092 (Open Web Text)

Max Activating Token Index: 387

Text #16

Max Range: 1.9735. Min Range: -1.9735

Max Act: 1.8359. Min Act: -0.1700

Data Index: 1620722 (Open Web Text)

Max Activating Token Index: 69

Text #17

Max Range: 1.9735. Min Range: -1.9735

Max Act: 1.8297. Min Act: -0.1700

Data Index: 6622195 (Open Web Text)

Max Activating Token Index: 543

Text #18

Max Range: 1.9735. Min Range: -1.9735

Max Act: 1.8318. Min Act: -0.1700

Data Index: 7716520 (Open Web Text)

Max Activating Token Index: 368

Text #19

Max Range: 1.9735. Min Range: -1.9735

Max Act: 1.8353. Min Act: -0.1700

Data Index: 1642660 (Open Web Text)

Max Activating Token Index: 66