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

Dataset: Open Web Text

Neuron 1190 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: 3.6570. Min Range: -3.6570

Max Act: 3.6570. Min Act: -0.1700

Data Index: 4587 (Open Web Text)

Max Activating Token Index: 114

Text #1

Max Range: 3.6570. Min Range: -3.6570

Max Act: 3.4241. Min Act: -0.1700

Data Index: 3311987 (Open Web Text)

Max Activating Token Index: 74

Text #2

Max Range: 3.6570. Min Range: -3.6570

Max Act: 3.4145. Min Act: -0.1700

Data Index: 635455 (Open Web Text)

Max Activating Token Index: 37

Text #3

Max Range: 3.6570. Min Range: -3.6570

Max Act: 3.2030. Min Act: -0.1700

Data Index: 6601956 (Open Web Text)

Max Activating Token Index: 1007

Text #4

Max Range: 3.6570. Min Range: -3.6570

Max Act: 3.2247. Min Act: -0.1700

Data Index: 343929 (Open Web Text)

Max Activating Token Index: 303

Text #5

Max Range: 3.6570. Min Range: -3.6570

Max Act: 3.2238. Min Act: -0.1700

Data Index: 531256 (Open Web Text)

Max Activating Token Index: 743

Text #6

Max Range: 3.6570. Min Range: -3.6570

Max Act: 3.1671. Min Act: -0.1700

Data Index: 5540579 (Open Web Text)

Max Activating Token Index: 544

Text #7

Max Range: 3.6570. Min Range: -3.6570

Max Act: 3.1041. Min Act: -0.1700

Data Index: 1665092 (Open Web Text)

Max Activating Token Index: 528

Text #8

Max Range: 3.6570. Min Range: -3.6570

Max Act: 3.1394. Min Act: -0.1700

Data Index: 4717248 (Open Web Text)

Max Activating Token Index: 624

Text #9

Max Range: 3.6570. Min Range: -3.6570

Max Act: 3.0557. Min Act: -0.1700

Data Index: 2572648 (Open Web Text)

Max Activating Token Index: 442

Text #10

Max Range: 3.6570. Min Range: -3.6570

Max Act: 3.0647. Min Act: -0.1700

Data Index: 1208070 (Open Web Text)

Max Activating Token Index: 464

Text #11

Max Range: 3.6570. Min Range: -3.6570

Max Act: 3.0089. Min Act: -0.1700

Data Index: 4096279 (Open Web Text)

Max Activating Token Index: 157

Text #12

Max Range: 3.6570. Min Range: -3.6570

Max Act: 3.0389. Min Act: -0.1700

Data Index: 5540564 (Open Web Text)

Max Activating Token Index: 545

Text #13

Max Range: 3.6570. Min Range: -3.6570

Max Act: 3.0238. Min Act: -0.1700

Data Index: 787865 (Open Web Text)

Max Activating Token Index: 67

Text #14

Max Range: 3.6570. Min Range: -3.6570

Max Act: 3.0764. Min Act: -0.1700

Data Index: 7563885 (Open Web Text)

Max Activating Token Index: 696

Text #15

Max Range: 3.6570. Min Range: -3.6570

Max Act: 2.9425. Min Act: -0.1700

Data Index: 5098929 (Open Web Text)

Max Activating Token Index: 43

Text #16

Max Range: 3.6570. Min Range: -3.6570

Max Act: 3.0103. Min Act: -0.1700

Data Index: 5995962 (Open Web Text)

Max Activating Token Index: 801

Text #17

Max Range: 3.6570. Min Range: -3.6570

Max Act: 2.9841. Min Act: -0.1700

Data Index: 7034691 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 3.6570. Min Range: -3.6570

Max Act: 2.9124. Min Act: -0.1700

Data Index: 2713470 (Open Web Text)

Max Activating Token Index: 933

Text #19

Max Range: 3.6570. Min Range: -3.6570

Max Act: 2.9593. Min Act: -0.1700

Data Index: 3488411 (Open Web Text)

Max Activating Token Index: 10