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

Dataset: Open Web Text

Neuron 257 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: 3.4091. Min Range: -3.4091

Max Act: 3.4091. Min Act: -0.1700

Data Index: 2403434 (Open Web Text)

Max Activating Token Index: 120

Text #1

Max Range: 3.4091. Min Range: -3.4091

Max Act: 3.2427. Min Act: -0.1700

Data Index: 6248978 (Open Web Text)

Max Activating Token Index: 357

Text #2

Max Range: 3.4091. Min Range: -3.4091

Max Act: 3.2494. Min Act: -0.1700

Data Index: 8284540 (Open Web Text)

Max Activating Token Index: 663

Text #3

Max Range: 3.4091. Min Range: -3.4091

Max Act: 3.2208. Min Act: -0.1700

Data Index: 5411951 (Open Web Text)

Max Activating Token Index: 643

Text #4

Max Range: 3.4091. Min Range: -3.4091

Max Act: 3.2345. Min Act: -0.1700

Data Index: 5268088 (Open Web Text)

Max Activating Token Index: 432

Text #5

Max Range: 3.4091. Min Range: -3.4091

Max Act: 3.2311. Min Act: -0.1700

Data Index: 5891071 (Open Web Text)

Max Activating Token Index: 897

Text #6

Max Range: 3.4091. Min Range: -3.4091

Max Act: 3.2017. Min Act: -0.1700

Data Index: 7603420 (Open Web Text)

Max Activating Token Index: 189

Text #7

Max Range: 3.4091. Min Range: -3.4091

Max Act: 3.2033. Min Act: -0.1700

Data Index: 7075222 (Open Web Text)

Max Activating Token Index: 735

Text #8

Max Range: 3.4091. Min Range: -3.4091

Max Act: 3.1672. Min Act: -0.1700

Data Index: 7495224 (Open Web Text)

Max Activating Token Index: 523

Text #9

Max Range: 3.4091. Min Range: -3.4091

Max Act: 3.1870. Min Act: -0.1700

Data Index: 8404862 (Open Web Text)

Max Activating Token Index: 393

Text #10

Max Range: 3.4091. Min Range: -3.4091

Max Act: 3.1532. Min Act: -0.1700

Data Index: 5014985 (Open Web Text)

Max Activating Token Index: 755

Text #11

Max Range: 3.4091. Min Range: -3.4091

Max Act: 3.1371. Min Act: -0.1700

Data Index: 8435146 (Open Web Text)

Max Activating Token Index: 843

Text #12

Max Range: 3.4091. Min Range: -3.4091

Max Act: 3.1509. Min Act: -0.1700

Data Index: 6736525 (Open Web Text)

Max Activating Token Index: 62

Text #13

Max Range: 3.4091. Min Range: -3.4091

Max Act: 3.1501. Min Act: -0.1700

Data Index: 8333084 (Open Web Text)

Max Activating Token Index: 195

Text #14

Max Range: 3.4091. Min Range: -3.4091

Max Act: 3.1602. Min Act: -0.1700

Data Index: 1994291 (Open Web Text)

Max Activating Token Index: 58

Text #15

Max Range: 3.4091. Min Range: -3.4091

Max Act: 3.1482. Min Act: -0.1700

Data Index: 1430456 (Open Web Text)

Max Activating Token Index: 81

Text #16

Max Range: 3.4091. Min Range: -3.4091

Max Act: 3.1670. Min Act: -0.1700

Data Index: 7593604 (Open Web Text)

Max Activating Token Index: 520

Text #17

Max Range: 3.4091. Min Range: -3.4091

Max Act: 3.1117. Min Act: -0.1700

Data Index: 7835688 (Open Web Text)

Max Activating Token Index: 442

Text #18

Max Range: 3.4091. Min Range: -3.4091

Max Act: 3.1417. Min Act: -0.1700

Data Index: 8198655 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 3.4091. Min Range: -3.4091

Max Act: 3.1325. Min Act: -0.1700

Data Index: 7389545 (Open Web Text)

Max Activating Token Index: 23