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

Dataset: Open Web Text

Neuron 623 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: 3.3569. Min Range: -3.3569

Max Act: 3.3569. Min Act: -0.1700

Data Index: 1388910 (Open Web Text)

Max Activating Token Index: 620

Text #1

Max Range: 3.3569. Min Range: -3.3569

Max Act: 3.3361. Min Act: -0.1700

Data Index: 4337998 (Open Web Text)

Max Activating Token Index: 916

Text #2

Max Range: 3.3569. Min Range: -3.3569

Max Act: 3.3015. Min Act: -0.1700

Data Index: 5491750 (Open Web Text)

Max Activating Token Index: 718

Text #3

Max Range: 3.3569. Min Range: -3.3569

Max Act: 3.2877. Min Act: -0.1700

Data Index: 7012202 (Open Web Text)

Max Activating Token Index: 348

Text #4

Max Range: 3.3569. Min Range: -3.3569

Max Act: 3.2326. Min Act: -0.1700

Data Index: 3249989 (Open Web Text)

Max Activating Token Index: 328

Text #5

Max Range: 3.3569. Min Range: -3.3569

Max Act: 3.2502. Min Act: -0.1700

Data Index: 537060 (Open Web Text)

Max Activating Token Index: 77

Text #6

Max Range: 3.3569. Min Range: -3.3569

Max Act: 3.2140. Min Act: -0.1700

Data Index: 5552808 (Open Web Text)

Max Activating Token Index: 550

Text #7

Max Range: 3.3569. Min Range: -3.3569

Max Act: 3.2073. Min Act: -0.1700

Data Index: 7429637 (Open Web Text)

Max Activating Token Index: 295

Text #8

Max Range: 3.3569. Min Range: -3.3569

Max Act: 3.1994. Min Act: -0.1700

Data Index: 8758307 (Open Web Text)

Max Activating Token Index: 831

Text #9

Max Range: 3.3569. Min Range: -3.3569

Max Act: 3.1774. Min Act: -0.1700

Data Index: 7880904 (Open Web Text)

Max Activating Token Index: 470

Text #10

Max Range: 3.3569. Min Range: -3.3569

Max Act: 3.1882. Min Act: -0.1700

Data Index: 1318407 (Open Web Text)

Max Activating Token Index: 682

Text #11

Max Range: 3.3569. Min Range: -3.3569

Max Act: 3.1716. Min Act: -0.1700

Data Index: 7661069 (Open Web Text)

Max Activating Token Index: 1018

Text #12

Max Range: 3.3569. Min Range: -3.3569

Max Act: 3.1858. Min Act: -0.1700

Data Index: 3235100 (Open Web Text)

Max Activating Token Index: 511

Text #13

Max Range: 3.3569. Min Range: -3.3569

Max Act: 3.1416. Min Act: -0.1700

Data Index: 950504 (Open Web Text)

Max Activating Token Index: 104

Text #14

Max Range: 3.3569. Min Range: -3.3569

Max Act: 3.1498. Min Act: -0.1700

Data Index: 2637027 (Open Web Text)

Max Activating Token Index: 503

Text #15

Max Range: 3.3569. Min Range: -3.3569

Max Act: 3.1419. Min Act: -0.1700

Data Index: 2685900 (Open Web Text)

Max Activating Token Index: 972

Text #16

Max Range: 3.3569. Min Range: -3.3569

Max Act: 3.1475. Min Act: -0.1700

Data Index: 1305952 (Open Web Text)

Max Activating Token Index: 776

Text #17

Max Range: 3.3569. Min Range: -3.3569

Max Act: 3.1708. Min Act: -0.1700

Data Index: 8475829 (Open Web Text)

Max Activating Token Index: 795

Text #18

Max Range: 3.3569. Min Range: -3.3569

Max Act: 3.1161. Min Act: -0.1700

Data Index: 295111 (Open Web Text)

Max Activating Token Index: 915

Text #19

Max Range: 3.3569. Min Range: -3.3569

Max Act: 3.1603. Min Act: -0.1700

Data Index: 8309107 (Open Web Text)

Max Activating Token Index: 164