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

Dataset: Open Web Text

Neuron 426 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: 3.4622. Min Range: -3.4622

Max Act: 3.4599. Min Act: -0.1700

Data Index: 5282266 (Open Web Text)

Max Activating Token Index: 374

Text #1

Max Range: 3.4622. Min Range: -3.4622

Max Act: 3.4622. Min Act: -0.1700

Data Index: 6349520 (Open Web Text)

Max Activating Token Index: 428

Text #2

Max Range: 3.4622. Min Range: -3.4622

Max Act: 3.3771. Min Act: -0.1700

Data Index: 3942031 (Open Web Text)

Max Activating Token Index: 874

Text #3

Max Range: 3.4622. Min Range: -3.4622

Max Act: 3.3354. Min Act: -0.1700

Data Index: 7339375 (Open Web Text)

Max Activating Token Index: 508

Text #4

Max Range: 3.4622. Min Range: -3.4622

Max Act: 3.3205. Min Act: -0.1700

Data Index: 3924255 (Open Web Text)

Max Activating Token Index: 340

Text #5

Max Range: 3.4622. Min Range: -3.4622

Max Act: 3.3001. Min Act: -0.1700

Data Index: 5754217 (Open Web Text)

Max Activating Token Index: 84

Text #6

Max Range: 3.4622. Min Range: -3.4622

Max Act: 3.2592. Min Act: -0.1700

Data Index: 5175444 (Open Web Text)

Max Activating Token Index: 326

Text #7

Max Range: 3.4622. Min Range: -3.4622

Max Act: 3.2394. Min Act: -0.1700

Data Index: 4268211 (Open Web Text)

Max Activating Token Index: 575

Text #8

Max Range: 3.4622. Min Range: -3.4622

Max Act: 3.2604. Min Act: -0.1700

Data Index: 2723968 (Open Web Text)

Max Activating Token Index: 277

Text #9

Max Range: 3.4622. Min Range: -3.4622

Max Act: 3.2523. Min Act: -0.1700

Data Index: 6072104 (Open Web Text)

Max Activating Token Index: 604

Text #10

Max Range: 3.4622. Min Range: -3.4622

Max Act: 3.2351. Min Act: -0.1700

Data Index: 4311452 (Open Web Text)

Max Activating Token Index: 66

Text #11

Max Range: 3.4622. Min Range: -3.4622

Max Act: 3.2221. Min Act: -0.1700

Data Index: 1073071 (Open Web Text)

Max Activating Token Index: 580

Text #12

Max Range: 3.4622. Min Range: -3.4622

Max Act: 3.2290. Min Act: -0.1700

Data Index: 3051789 (Open Web Text)

Max Activating Token Index: 673

Text #13

Max Range: 3.4622. Min Range: -3.4622

Max Act: 3.2156. Min Act: -0.1700

Data Index: 5290934 (Open Web Text)

Max Activating Token Index: 630

Text #14

Max Range: 3.4622. Min Range: -3.4622

Max Act: 3.2256. Min Act: -0.1700

Data Index: 5453784 (Open Web Text)

Max Activating Token Index: 552

Text #15

Max Range: 3.4622. Min Range: -3.4622

Max Act: 3.2273. Min Act: -0.1700

Data Index: 649091 (Open Web Text)

Max Activating Token Index: 561

Text #16

Max Range: 3.4622. Min Range: -3.4622

Max Act: 3.2255. Min Act: -0.1700

Data Index: 7357125 (Open Web Text)

Max Activating Token Index: 596

Text #17

Max Range: 3.4622. Min Range: -3.4622

Max Act: 3.2302. Min Act: -0.1700

Data Index: 2198609 (Open Web Text)

Max Activating Token Index: 955

Text #18

Max Range: 3.4622. Min Range: -3.4622

Max Act: 3.1999. Min Act: -0.1700

Data Index: 7576854 (Open Web Text)

Max Activating Token Index: 89

Text #19

Max Range: 3.4622. Min Range: -3.4622

Max Act: 3.1595. Min Act: -0.1700

Data Index: 5609112 (Open Web Text)

Max Activating Token Index: 575