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

Dataset: Open Web Text

Neuron 2905 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: 4.3946. Min Range: -4.3946

Max Act: 4.3946. Min Act: -0.1700

Data Index: 2534884 (Open Web Text)

Max Activating Token Index: 306

Text #1

Max Range: 4.3946. Min Range: -4.3946

Max Act: 4.3027. Min Act: -0.1700

Data Index: 3864766 (Open Web Text)

Max Activating Token Index: 421

Text #2

Max Range: 4.3946. Min Range: -4.3946

Max Act: 4.2715. Min Act: -0.1700

Data Index: 3864769 (Open Web Text)

Max Activating Token Index: 666

Text #3

Max Range: 4.3946. Min Range: -4.3946

Max Act: 4.2564. Min Act: -0.1700

Data Index: 1184804 (Open Web Text)

Max Activating Token Index: 124

Text #4

Max Range: 4.3946. Min Range: -4.3946

Max Act: 4.1916. Min Act: -0.1700

Data Index: 3864776 (Open Web Text)

Max Activating Token Index: 805

Text #5

Max Range: 4.3946. Min Range: -4.3946

Max Act: 4.2174. Min Act: -0.1700

Data Index: 3160610 (Open Web Text)

Max Activating Token Index: 993

Text #6

Max Range: 4.3946. Min Range: -4.3946

Max Act: 4.1701. Min Act: -0.1700

Data Index: 2291728 (Open Web Text)

Max Activating Token Index: 654

Text #7

Max Range: 4.3946. Min Range: -4.3946

Max Act: 4.1980. Min Act: -0.1700

Data Index: 5510612 (Open Web Text)

Max Activating Token Index: 27

Text #8

Max Range: 4.3946. Min Range: -4.3946

Max Act: 4.1432. Min Act: -0.1700

Data Index: 7436902 (Open Web Text)

Max Activating Token Index: 730

Text #9

Max Range: 4.3946. Min Range: -4.3946

Max Act: 4.1305. Min Act: -0.1700

Data Index: 2843188 (Open Web Text)

Max Activating Token Index: 152

Text #10

Max Range: 4.3946. Min Range: -4.3946

Max Act: 4.1534. Min Act: -0.1700

Data Index: 7445499 (Open Web Text)

Max Activating Token Index: 840

Text #11

Max Range: 4.3946. Min Range: -4.3946

Max Act: 4.1527. Min Act: -0.1700

Data Index: 3864771 (Open Web Text)

Max Activating Token Index: 519

Text #12

Max Range: 4.3946. Min Range: -4.3946

Max Act: 4.1480. Min Act: -0.1700

Data Index: 2883136 (Open Web Text)

Max Activating Token Index: 476

Text #13

Max Range: 4.3946. Min Range: -4.3946

Max Act: 4.1476. Min Act: -0.1700

Data Index: 5017965 (Open Web Text)

Max Activating Token Index: 440

Text #14

Max Range: 4.3946. Min Range: -4.3946

Max Act: 4.1484. Min Act: -0.1700

Data Index: 3413996 (Open Web Text)

Max Activating Token Index: 478

Text #15

Max Range: 4.3946. Min Range: -4.3946

Max Act: 4.1559. Min Act: -0.1700

Data Index: 5692203 (Open Web Text)

Max Activating Token Index: 288

Text #16

Max Range: 4.3946. Min Range: -4.3946

Max Act: 4.1731. Min Act: -0.1700

Data Index: 3864781 (Open Web Text)

Max Activating Token Index: 1013

Text #17

Max Range: 4.3946. Min Range: -4.3946

Max Act: 4.1548. Min Act: -0.1700

Data Index: 3864775 (Open Web Text)

Max Activating Token Index: 158

Text #18

Max Range: 4.3946. Min Range: -4.3946

Max Act: 4.1492. Min Act: -0.1700

Data Index: 6268813 (Open Web Text)

Max Activating Token Index: 280

Text #19

Max Range: 4.3946. Min Range: -4.3946

Max Act: 4.1389. Min Act: -0.1700

Data Index: 3864764 (Open Web Text)

Max Activating Token Index: 394