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

Dataset: Open Web Text

Neuron 1849 in Layer 6

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: 7.0934. Min Range: -7.0934

Max Act: 7.0934. Min Act: -0.1700

Data Index: 262285 (Open Web Text)

Max Activating Token Index: 390

Text #1

Max Range: 7.0934. Min Range: -7.0934

Max Act: 6.8442. Min Act: -0.1700

Data Index: 5892955 (Open Web Text)

Max Activating Token Index: 512

Text #2

Max Range: 7.0934. Min Range: -7.0934

Max Act: 6.7947. Min Act: -0.1700

Data Index: 4061589 (Open Web Text)

Max Activating Token Index: 962

Text #3

Max Range: 7.0934. Min Range: -7.0934

Max Act: 6.7127. Min Act: -0.1700

Data Index: 5567459 (Open Web Text)

Max Activating Token Index: 75

Text #4

Max Range: 7.0934. Min Range: -7.0934

Max Act: 6.6830. Min Act: -0.1700

Data Index: 5727691 (Open Web Text)

Max Activating Token Index: 306

Text #5

Max Range: 7.0934. Min Range: -7.0934

Max Act: 6.6472. Min Act: -0.1700

Data Index: 4332436 (Open Web Text)

Max Activating Token Index: 481

Text #6

Max Range: 7.0934. Min Range: -7.0934

Max Act: 6.6582. Min Act: -0.1700

Data Index: 6615564 (Open Web Text)

Max Activating Token Index: 953

Text #7

Max Range: 7.0934. Min Range: -7.0934

Max Act: 6.6447. Min Act: -0.1700

Data Index: 4554382 (Open Web Text)

Max Activating Token Index: 961

Text #8

Max Range: 7.0934. Min Range: -7.0934

Max Act: 6.6306. Min Act: -0.1700

Data Index: 7123850 (Open Web Text)

Max Activating Token Index: 149

Text #9

Max Range: 7.0934. Min Range: -7.0934

Max Act: 6.6185. Min Act: -0.1700

Data Index: 323171 (Open Web Text)

Max Activating Token Index: 614

Text #10

Max Range: 7.0934. Min Range: -7.0934

Max Act: 6.6323. Min Act: -0.1700

Data Index: 3603727 (Open Web Text)

Max Activating Token Index: 937

Text #11

Max Range: 7.0934. Min Range: -7.0934

Max Act: 6.6086. Min Act: -0.1700

Data Index: 1419695 (Open Web Text)

Max Activating Token Index: 281

Text #12

Max Range: 7.0934. Min Range: -7.0934

Max Act: 6.5929. Min Act: -0.1700

Data Index: 1532233 (Open Web Text)

Max Activating Token Index: 262

Text #13

Max Range: 7.0934. Min Range: -7.0934

Max Act: 6.5286. Min Act: -0.1700

Data Index: 5297836 (Open Web Text)

Max Activating Token Index: 241

Text #14

Max Range: 7.0934. Min Range: -7.0934

Max Act: 6.5761. Min Act: -0.1700

Data Index: 8427307 (Open Web Text)

Max Activating Token Index: 392

Text #15

Max Range: 7.0934. Min Range: -7.0934

Max Act: 6.5712. Min Act: -0.1700

Data Index: 142516 (Open Web Text)

Max Activating Token Index: 48

Text #16

Max Range: 7.0934. Min Range: -7.0934

Max Act: 6.5746. Min Act: -0.1700

Data Index: 5808671 (Open Web Text)

Max Activating Token Index: 114

Text #17

Max Range: 7.0934. Min Range: -7.0934

Max Act: 6.5967. Min Act: -0.1700

Data Index: 2579870 (Open Web Text)

Max Activating Token Index: 378

Text #18

Max Range: 7.0934. Min Range: -7.0934

Max Act: 6.4852. Min Act: -0.1700

Data Index: 2024011 (Open Web Text)

Max Activating Token Index: 888

Text #19

Max Range: 7.0934. Min Range: -7.0934

Max Act: 6.4581. Min Act: -0.1700

Data Index: 5281688 (Open Web Text)

Max Activating Token Index: 425