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

Dataset: Open Web Text

Neuron 2647 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: 3.3890. Min Range: -3.3890

Max Act: 3.3890. Min Act: -0.1700

Data Index: 7585332 (Open Web Text)

Max Activating Token Index: 922

Text #1

Max Range: 3.3890. Min Range: -3.3890

Max Act: 3.3458. Min Act: -0.1700

Data Index: 4074879 (Open Web Text)

Max Activating Token Index: 428

Text #2

Max Range: 3.3890. Min Range: -3.3890

Max Act: 3.3631. Min Act: -0.1700

Data Index: 4826033 (Open Web Text)

Max Activating Token Index: 208

Text #3

Max Range: 3.3890. Min Range: -3.3890

Max Act: 3.3364. Min Act: -0.1700

Data Index: 3091337 (Open Web Text)

Max Activating Token Index: 869

Text #4

Max Range: 3.3890. Min Range: -3.3890

Max Act: 3.3105. Min Act: -0.1700

Data Index: 3021041 (Open Web Text)

Max Activating Token Index: 636

Text #5

Max Range: 3.3890. Min Range: -3.3890

Max Act: 3.3031. Min Act: -0.1700

Data Index: 7070968 (Open Web Text)

Max Activating Token Index: 342

Text #6

Max Range: 3.3890. Min Range: -3.3890

Max Act: 3.3146. Min Act: -0.1700

Data Index: 6859 (Open Web Text)

Max Activating Token Index: 402

Text #7

Max Range: 3.3890. Min Range: -3.3890

Max Act: 3.2970. Min Act: -0.1700

Data Index: 7660468 (Open Web Text)

Max Activating Token Index: 204

Text #8

Max Range: 3.3890. Min Range: -3.3890

Max Act: 3.3017. Min Act: -0.1700

Data Index: 537505 (Open Web Text)

Max Activating Token Index: 599

Text #9

Max Range: 3.3890. Min Range: -3.3890

Max Act: 3.3038. Min Act: -0.1700

Data Index: 4789079 (Open Web Text)

Max Activating Token Index: 814

Text #10

Max Range: 3.3890. Min Range: -3.3890

Max Act: 3.3055. Min Act: -0.1700

Data Index: 8149724 (Open Web Text)

Max Activating Token Index: 595

Text #11

Max Range: 3.3890. Min Range: -3.3890

Max Act: 3.2806. Min Act: -0.1700

Data Index: 6238417 (Open Web Text)

Max Activating Token Index: 706

Text #12

Max Range: 3.3890. Min Range: -3.3890

Max Act: 3.3298. Min Act: -0.1700

Data Index: 6874238 (Open Web Text)

Max Activating Token Index: 927

Text #13

Max Range: 3.3890. Min Range: -3.3890

Max Act: 3.2925. Min Act: -0.1700

Data Index: 507952 (Open Web Text)

Max Activating Token Index: 726

Text #14

Max Range: 3.3890. Min Range: -3.3890

Max Act: 3.2809. Min Act: -0.1700

Data Index: 3547740 (Open Web Text)

Max Activating Token Index: 804

Text #15

Max Range: 3.3890. Min Range: -3.3890

Max Act: 3.2736. Min Act: -0.1700

Data Index: 1669590 (Open Web Text)

Max Activating Token Index: 490

Text #16

Max Range: 3.3890. Min Range: -3.3890

Max Act: 3.2779. Min Act: -0.1700

Data Index: 5012190 (Open Web Text)

Max Activating Token Index: 416

Text #17

Max Range: 3.3890. Min Range: -3.3890

Max Act: 3.2656. Min Act: -0.1700

Data Index: 71276 (Open Web Text)

Max Activating Token Index: 897

Text #18

Max Range: 3.3890. Min Range: -3.3890

Max Act: 3.2960. Min Act: -0.1700

Data Index: 4006879 (Open Web Text)

Max Activating Token Index: 532

Text #19

Max Range: 3.3890. Min Range: -3.3890

Max Act: 3.2485. Min Act: -0.1700

Data Index: 1017174 (Open Web Text)

Max Activating Token Index: 734