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

Dataset: Open Web Text

Neuron 2042 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: 3.3643. Min Range: -3.3643

Max Act: 3.3643. Min Act: -0.1700

Data Index: 2428368 (Open Web Text)

Max Activating Token Index: 550

Text #1

Max Range: 3.3643. Min Range: -3.3643

Max Act: 3.2913. Min Act: -0.1700

Data Index: 4729121 (Open Web Text)

Max Activating Token Index: 543

Text #2

Max Range: 3.3643. Min Range: -3.3643

Max Act: 3.2613. Min Act: -0.1700

Data Index: 5042621 (Open Web Text)

Max Activating Token Index: 1009

Text #3

Max Range: 3.3643. Min Range: -3.3643

Max Act: 3.2257. Min Act: -0.1700

Data Index: 942101 (Open Web Text)

Max Activating Token Index: 933

Text #4

Max Range: 3.3643. Min Range: -3.3643

Max Act: 3.1714. Min Act: -0.1700

Data Index: 5142107 (Open Web Text)

Max Activating Token Index: 671

Text #5

Max Range: 3.3643. Min Range: -3.3643

Max Act: 3.1924. Min Act: -0.1700

Data Index: 4992364 (Open Web Text)

Max Activating Token Index: 804

Text #6

Max Range: 3.3643. Min Range: -3.3643

Max Act: 3.1599. Min Act: -0.1700

Data Index: 8002924 (Open Web Text)

Max Activating Token Index: 533

Text #7

Max Range: 3.3643. Min Range: -3.3643

Max Act: 3.1689. Min Act: -0.1700

Data Index: 2711782 (Open Web Text)

Max Activating Token Index: 953

Text #8

Max Range: 3.3643. Min Range: -3.3643

Max Act: 3.1576. Min Act: -0.1700

Data Index: 2211620 (Open Web Text)

Max Activating Token Index: 1022

Text #9

Max Range: 3.3643. Min Range: -3.3643

Max Act: 3.1336. Min Act: -0.1700

Data Index: 1748251 (Open Web Text)

Max Activating Token Index: 880

Text #10

Max Range: 3.3643. Min Range: -3.3643

Max Act: 3.1034. Min Act: -0.1700

Data Index: 6109943 (Open Web Text)

Max Activating Token Index: 262

Text #11

Max Range: 3.3643. Min Range: -3.3643

Max Act: 3.0662. Min Act: -0.1700

Data Index: 6141117 (Open Web Text)

Max Activating Token Index: 207

Text #12

Max Range: 3.3643. Min Range: -3.3643

Max Act: 3.0687. Min Act: -0.1700

Data Index: 65676 (Open Web Text)

Max Activating Token Index: 592

Text #13

Max Range: 3.3643. Min Range: -3.3643

Max Act: 3.0613. Min Act: -0.1700

Data Index: 6163185 (Open Web Text)

Max Activating Token Index: 322

Text #14

Max Range: 3.3643. Min Range: -3.3643

Max Act: 3.0589. Min Act: -0.1700

Data Index: 6797235 (Open Web Text)

Max Activating Token Index: 184

Text #15

Max Range: 3.3643. Min Range: -3.3643

Max Act: 3.0317. Min Act: -0.1700

Data Index: 3812760 (Open Web Text)

Max Activating Token Index: 576

Text #16

Max Range: 3.3643. Min Range: -3.3643

Max Act: 3.0361. Min Act: -0.1700

Data Index: 8439082 (Open Web Text)

Max Activating Token Index: 471

Text #17

Max Range: 3.3643. Min Range: -3.3643

Max Act: 3.0331. Min Act: -0.1700

Data Index: 5263541 (Open Web Text)

Max Activating Token Index: 447

Text #18

Max Range: 3.3643. Min Range: -3.3643

Max Act: 3.0456. Min Act: -0.1700

Data Index: 6264404 (Open Web Text)

Max Activating Token Index: 960

Text #19

Max Range: 3.3643. Min Range: -3.3643

Max Act: 3.0037. Min Act: -0.1700

Data Index: 3841419 (Open Web Text)

Max Activating Token Index: 644