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

Dataset: Open Web Text

Neuron 2811 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: 3.1982. Min Range: -3.1982

Max Act: 3.1982. Min Act: -0.1700

Data Index: 6558193 (Open Web Text)

Max Activating Token Index: 603

Text #1

Max Range: 3.1982. Min Range: -3.1982

Max Act: 3.1917. Min Act: -0.1700

Data Index: 5888809 (Open Web Text)

Max Activating Token Index: 598

Text #2

Max Range: 3.1982. Min Range: -3.1982

Max Act: 3.1694. Min Act: -0.1700

Data Index: 1294046 (Open Web Text)

Max Activating Token Index: 569

Text #3

Max Range: 3.1982. Min Range: -3.1982

Max Act: 3.1681. Min Act: -0.1700

Data Index: 2705992 (Open Web Text)

Max Activating Token Index: 452

Text #4

Max Range: 3.1982. Min Range: -3.1982

Max Act: 3.1219. Min Act: -0.1700

Data Index: 6976694 (Open Web Text)

Max Activating Token Index: 993

Text #5

Max Range: 3.1982. Min Range: -3.1982

Max Act: 3.1203. Min Act: -0.1700

Data Index: 3887964 (Open Web Text)

Max Activating Token Index: 251

Text #6

Max Range: 3.1982. Min Range: -3.1982

Max Act: 3.1318. Min Act: -0.1700

Data Index: 899852 (Open Web Text)

Max Activating Token Index: 352

Text #7

Max Range: 3.1982. Min Range: -3.1982

Max Act: 3.1270. Min Act: -0.1700

Data Index: 7494445 (Open Web Text)

Max Activating Token Index: 299

Text #8

Max Range: 3.1982. Min Range: -3.1982

Max Act: 3.0872. Min Act: -0.1700

Data Index: 6529576 (Open Web Text)

Max Activating Token Index: 602

Text #9

Max Range: 3.1982. Min Range: -3.1982

Max Act: 3.1093. Min Act: -0.1700

Data Index: 6720219 (Open Web Text)

Max Activating Token Index: 373

Text #10

Max Range: 3.1982. Min Range: -3.1982

Max Act: 3.1193. Min Act: -0.1700

Data Index: 6143450 (Open Web Text)

Max Activating Token Index: 953

Text #11

Max Range: 3.1982. Min Range: -3.1982

Max Act: 3.1005. Min Act: -0.1700

Data Index: 7129776 (Open Web Text)

Max Activating Token Index: 711

Text #12

Max Range: 3.1982. Min Range: -3.1982

Max Act: 3.0776. Min Act: -0.1700

Data Index: 4524965 (Open Web Text)

Max Activating Token Index: 579

Text #13

Max Range: 3.1982. Min Range: -3.1982

Max Act: 3.0912. Min Act: -0.1700

Data Index: 1745167 (Open Web Text)

Max Activating Token Index: 1009

Text #14

Max Range: 3.1982. Min Range: -3.1982

Max Act: 3.0890. Min Act: -0.1700

Data Index: 5434877 (Open Web Text)

Max Activating Token Index: 977

Text #15

Max Range: 3.1982. Min Range: -3.1982

Max Act: 3.0912. Min Act: -0.1700

Data Index: 6114921 (Open Web Text)

Max Activating Token Index: 807

Text #16

Max Range: 3.1982. Min Range: -3.1982

Max Act: 3.0594. Min Act: -0.1700

Data Index: 598350 (Open Web Text)

Max Activating Token Index: 331

Text #17

Max Range: 3.1982. Min Range: -3.1982

Max Act: 3.0393. Min Act: -0.1700

Data Index: 652177 (Open Web Text)

Max Activating Token Index: 409

Text #18

Max Range: 3.1982. Min Range: -3.1982

Max Act: 3.0569. Min Act: -0.1700

Data Index: 2064925 (Open Web Text)

Max Activating Token Index: 665

Text #19

Max Range: 3.1982. Min Range: -3.1982

Max Act: 3.0515. Min Act: -0.1700

Data Index: 8057654 (Open Web Text)

Max Activating Token Index: 1011