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

Dataset: Open Web Text

Neuron 927 in Layer 5

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: 4.2958. Min Range: -4.2958

Max Act: 4.2958. Min Act: -0.1700

Data Index: 5554588 (Open Web Text)

Max Activating Token Index: 790

Text #1

Max Range: 4.2958. Min Range: -4.2958

Max Act: 4.2115. Min Act: -0.1700

Data Index: 3809094 (Open Web Text)

Max Activating Token Index: 386

Text #2

Max Range: 4.2958. Min Range: -4.2958

Max Act: 4.1310. Min Act: -0.1700

Data Index: 16323 (Open Web Text)

Max Activating Token Index: 921

Text #3

Max Range: 4.2958. Min Range: -4.2958

Max Act: 4.1622. Min Act: -0.1700

Data Index: 5046856 (Open Web Text)

Max Activating Token Index: 144

Text #4

Max Range: 4.2958. Min Range: -4.2958

Max Act: 4.1069. Min Act: -0.1700

Data Index: 5853282 (Open Web Text)

Max Activating Token Index: 365

Text #5

Max Range: 4.2958. Min Range: -4.2958

Max Act: 4.1250. Min Act: -0.1700

Data Index: 3389448 (Open Web Text)

Max Activating Token Index: 525

Text #6

Max Range: 4.2958. Min Range: -4.2958

Max Act: 4.1250. Min Act: -0.1700

Data Index: 1587930 (Open Web Text)

Max Activating Token Index: 586

Text #7

Max Range: 4.2958. Min Range: -4.2958

Max Act: 4.0755. Min Act: -0.1700

Data Index: 6812491 (Open Web Text)

Max Activating Token Index: 621

Text #8

Max Range: 4.2958. Min Range: -4.2958

Max Act: 4.1002. Min Act: -0.1700

Data Index: 6540858 (Open Web Text)

Max Activating Token Index: 312

Text #9

Max Range: 4.2958. Min Range: -4.2958

Max Act: 4.0762. Min Act: -0.1700

Data Index: 1499346 (Open Web Text)

Max Activating Token Index: 206

Text #10

Max Range: 4.2958. Min Range: -4.2958

Max Act: 4.1210. Min Act: -0.1700

Data Index: 3561876 (Open Web Text)

Max Activating Token Index: 31

Text #11

Max Range: 4.2958. Min Range: -4.2958

Max Act: 4.1061. Min Act: -0.1700

Data Index: 5381746 (Open Web Text)

Max Activating Token Index: 425

Text #12

Max Range: 4.2958. Min Range: -4.2958

Max Act: 4.0773. Min Act: -0.1700

Data Index: 8383287 (Open Web Text)

Max Activating Token Index: 492

Text #13

Max Range: 4.2958. Min Range: -4.2958

Max Act: 4.0787. Min Act: -0.1700

Data Index: 3084720 (Open Web Text)

Max Activating Token Index: 434

Text #14

Max Range: 4.2958. Min Range: -4.2958

Max Act: 4.0405. Min Act: -0.1700

Data Index: 4462059 (Open Web Text)

Max Activating Token Index: 932

Text #15

Max Range: 4.2958. Min Range: -4.2958

Max Act: 4.0603. Min Act: -0.1700

Data Index: 1827420 (Open Web Text)

Max Activating Token Index: 853

Text #16

Max Range: 4.2958. Min Range: -4.2958

Max Act: 4.0946. Min Act: -0.1700

Data Index: 5617354 (Open Web Text)

Max Activating Token Index: 407

Text #17

Max Range: 4.2958. Min Range: -4.2958

Max Act: 4.0510. Min Act: -0.1700

Data Index: 4540318 (Open Web Text)

Max Activating Token Index: 34

Text #18

Max Range: 4.2958. Min Range: -4.2958

Max Act: 4.0965. Min Act: -0.1700

Data Index: 1791999 (Open Web Text)

Max Activating Token Index: 879

Text #19

Max Range: 4.2958. Min Range: -4.2958

Max Act: 4.0427. Min Act: -0.1700

Data Index: 5919654 (Open Web Text)

Max Activating Token Index: 327