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

Dataset: Open Web Text

Neuron 2598 in Layer 0

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: 4.0528. Min Range: -4.0528

Max Act: 4.0528. Min Act: -0.1700

Data Index: 5826615 (Open Web Text)

Max Activating Token Index: 46

Text #1

Max Range: 4.0528. Min Range: -4.0528

Max Act: 3.9965. Min Act: -0.1700

Data Index: 4468563 (Open Web Text)

Max Activating Token Index: 1019

Text #2

Max Range: 4.0528. Min Range: -4.0528

Max Act: 3.9708. Min Act: -0.1700

Data Index: 2139732 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.0528. Min Range: -4.0528

Max Act: 3.9778. Min Act: -0.1700

Data Index: 4493562 (Open Web Text)

Max Activating Token Index: 949

Text #4

Max Range: 4.0528. Min Range: -4.0528

Max Act: 3.9882. Min Act: -0.1700

Data Index: 7771683 (Open Web Text)

Max Activating Token Index: 54

Text #5

Max Range: 4.0528. Min Range: -4.0528

Max Act: 4.0037. Min Act: -0.1700

Data Index: 4569218 (Open Web Text)

Max Activating Token Index: 928

Text #6

Max Range: 4.0528. Min Range: -4.0528

Max Act: 3.9827. Min Act: -0.1700

Data Index: 7954639 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 4.0528. Min Range: -4.0528

Max Act: 3.9555. Min Act: -0.1700

Data Index: 1819195 (Open Web Text)

Max Activating Token Index: 511

Text #8

Max Range: 4.0528. Min Range: -4.0528

Max Act: 3.9378. Min Act: -0.1700

Data Index: 268677 (Open Web Text)

Max Activating Token Index: 14

Text #9

Max Range: 4.0528. Min Range: -4.0528

Max Act: 3.9574. Min Act: -0.1700

Data Index: 3688534 (Open Web Text)

Max Activating Token Index: 16

Text #10

Max Range: 4.0528. Min Range: -4.0528

Max Act: 3.9666. Min Act: -0.1700

Data Index: 3603487 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 4.0528. Min Range: -4.0528

Max Act: 3.9501. Min Act: -0.1700

Data Index: 7921969 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 4.0528. Min Range: -4.0528

Max Act: 3.9598. Min Act: -0.1700

Data Index: 1602081 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 4.0528. Min Range: -4.0528

Max Act: 3.9393. Min Act: -0.1700

Data Index: 2818670 (Open Web Text)

Max Activating Token Index: 859

Text #14

Max Range: 4.0528. Min Range: -4.0528

Max Act: 3.9618. Min Act: -0.1700

Data Index: 5557075 (Open Web Text)

Max Activating Token Index: 962

Text #15

Max Range: 4.0528. Min Range: -4.0528

Max Act: 3.9055. Min Act: -0.1700

Data Index: 887741 (Open Web Text)

Max Activating Token Index: 16

Text #16

Max Range: 4.0528. Min Range: -4.0528

Max Act: 3.9273. Min Act: -0.1700

Data Index: 3703096 (Open Web Text)

Max Activating Token Index: 858

Text #17

Max Range: 4.0528. Min Range: -4.0528

Max Act: 3.9058. Min Act: -0.1700

Data Index: 3923400 (Open Web Text)

Max Activating Token Index: 465

Text #18

Max Range: 4.0528. Min Range: -4.0528

Max Act: 3.9154. Min Act: -0.1700

Data Index: 4034004 (Open Web Text)

Max Activating Token Index: 667

Text #19

Max Range: 4.0528. Min Range: -4.0528

Max Act: 3.8957. Min Act: -0.1700

Data Index: 4470107 (Open Web Text)

Max Activating Token Index: 987