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

Dataset: Open Web Text

Neuron 1337 in Layer 3

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: 4.6884. Min Range: -4.6884

Max Act: 4.6884. Min Act: -0.1700

Data Index: 2389297 (Open Web Text)

Max Activating Token Index: 148

Text #1

Max Range: 4.6884. Min Range: -4.6884

Max Act: 4.6034. Min Act: -0.1700

Data Index: 3928394 (Open Web Text)

Max Activating Token Index: 1011

Text #2

Max Range: 4.6884. Min Range: -4.6884

Max Act: 4.5968. Min Act: -0.1700

Data Index: 991058 (Open Web Text)

Max Activating Token Index: 878

Text #3

Max Range: 4.6884. Min Range: -4.6884

Max Act: 4.5369. Min Act: -0.1700

Data Index: 3280621 (Open Web Text)

Max Activating Token Index: 944

Text #4

Max Range: 4.6884. Min Range: -4.6884

Max Act: 4.5163. Min Act: -0.1700

Data Index: 3928395 (Open Web Text)

Max Activating Token Index: 221

Text #5

Max Range: 4.6884. Min Range: -4.6884

Max Act: 4.4943. Min Act: -0.1700

Data Index: 7549778 (Open Web Text)

Max Activating Token Index: 597

Text #6

Max Range: 4.6884. Min Range: -4.6884

Max Act: 4.5335. Min Act: -0.1700

Data Index: 1609495 (Open Web Text)

Max Activating Token Index: 1004

Text #7

Max Range: 4.6884. Min Range: -4.6884

Max Act: 4.5100. Min Act: -0.1700

Data Index: 3121467 (Open Web Text)

Max Activating Token Index: 533

Text #8

Max Range: 4.6884. Min Range: -4.6884

Max Act: 4.5143. Min Act: -0.1700

Data Index: 5385287 (Open Web Text)

Max Activating Token Index: 118

Text #9

Max Range: 4.6884. Min Range: -4.6884

Max Act: 4.5205. Min Act: -0.1700

Data Index: 1482007 (Open Web Text)

Max Activating Token Index: 993

Text #10

Max Range: 4.6884. Min Range: -4.6884

Max Act: 4.5342. Min Act: -0.1700

Data Index: 1133659 (Open Web Text)

Max Activating Token Index: 743

Text #11

Max Range: 4.6884. Min Range: -4.6884

Max Act: 4.5160. Min Act: -0.1700

Data Index: 5094344 (Open Web Text)

Max Activating Token Index: 525

Text #12

Max Range: 4.6884. Min Range: -4.6884

Max Act: 4.5390. Min Act: -0.1700

Data Index: 6213307 (Open Web Text)

Max Activating Token Index: 431

Text #13

Max Range: 4.6884. Min Range: -4.6884

Max Act: 4.4704. Min Act: -0.1700

Data Index: 5235193 (Open Web Text)

Max Activating Token Index: 446

Text #14

Max Range: 4.6884. Min Range: -4.6884

Max Act: 4.4648. Min Act: -0.1700

Data Index: 6576131 (Open Web Text)

Max Activating Token Index: 390

Text #15

Max Range: 4.6884. Min Range: -4.6884

Max Act: 4.4619. Min Act: -0.1700

Data Index: 6689651 (Open Web Text)

Max Activating Token Index: 586

Text #16

Max Range: 4.6884. Min Range: -4.6884

Max Act: 4.4643. Min Act: -0.1700

Data Index: 6930980 (Open Web Text)

Max Activating Token Index: 484

Text #17

Max Range: 4.6884. Min Range: -4.6884

Max Act: 4.4940. Min Act: -0.1700

Data Index: 2032031 (Open Web Text)

Max Activating Token Index: 967

Text #18

Max Range: 4.6884. Min Range: -4.6884

Max Act: 4.4576. Min Act: -0.1700

Data Index: 7098588 (Open Web Text)

Max Activating Token Index: 536

Text #19

Max Range: 4.6884. Min Range: -4.6884

Max Act: 4.4930. Min Act: -0.1700

Data Index: 4627095 (Open Web Text)

Max Activating Token Index: 447