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

Dataset: Open Web Text

Neuron 1864 in Layer 3

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: 4.4958. Min Range: -4.4958

Max Act: 4.4958. Min Act: -0.1700

Data Index: 6366452 (Open Web Text)

Max Activating Token Index: 349

Text #1

Max Range: 4.4958. Min Range: -4.4958

Max Act: 4.2498. Min Act: -0.1700

Data Index: 3320643 (Open Web Text)

Max Activating Token Index: 488

Text #2

Max Range: 4.4958. Min Range: -4.4958

Max Act: 4.2036. Min Act: -0.1700

Data Index: 8214140 (Open Web Text)

Max Activating Token Index: 535

Text #3

Max Range: 4.4958. Min Range: -4.4958

Max Act: 4.1758. Min Act: -0.1700

Data Index: 3884112 (Open Web Text)

Max Activating Token Index: 497

Text #4

Max Range: 4.4958. Min Range: -4.4958

Max Act: 4.0657. Min Act: -0.1700

Data Index: 8508043 (Open Web Text)

Max Activating Token Index: 537

Text #5

Max Range: 4.4958. Min Range: -4.4958

Max Act: 4.1304. Min Act: -0.1700

Data Index: 3310852 (Open Web Text)

Max Activating Token Index: 837

Text #6

Max Range: 4.4958. Min Range: -4.4958

Max Act: 4.0767. Min Act: -0.1700

Data Index: 5472926 (Open Web Text)

Max Activating Token Index: 379

Text #7

Max Range: 4.4958. Min Range: -4.4958

Max Act: 4.0722. Min Act: -0.1700

Data Index: 5529308 (Open Web Text)

Max Activating Token Index: 953

Text #8

Max Range: 4.4958. Min Range: -4.4958

Max Act: 4.0468. Min Act: -0.1700

Data Index: 3278910 (Open Web Text)

Max Activating Token Index: 982

Text #9

Max Range: 4.4958. Min Range: -4.4958

Max Act: 4.0425. Min Act: -0.1700

Data Index: 2271974 (Open Web Text)

Max Activating Token Index: 513

Text #10

Max Range: 4.4958. Min Range: -4.4958

Max Act: 4.1079. Min Act: -0.1700

Data Index: 3583484 (Open Web Text)

Max Activating Token Index: 641

Text #11

Max Range: 4.4958. Min Range: -4.4958

Max Act: 4.0505. Min Act: -0.1700

Data Index: 6996767 (Open Web Text)

Max Activating Token Index: 237

Text #12

Max Range: 4.4958. Min Range: -4.4958

Max Act: 4.0228. Min Act: -0.1700

Data Index: 1309981 (Open Web Text)

Max Activating Token Index: 652

Text #13

Max Range: 4.4958. Min Range: -4.4958

Max Act: 4.0465. Min Act: -0.1700

Data Index: 6602784 (Open Web Text)

Max Activating Token Index: 637

Text #14

Max Range: 4.4958. Min Range: -4.4958

Max Act: 3.9605. Min Act: -0.1700

Data Index: 6029334 (Open Web Text)

Max Activating Token Index: 607

Text #15

Max Range: 4.4958. Min Range: -4.4958

Max Act: 4.0058. Min Act: -0.1700

Data Index: 803260 (Open Web Text)

Max Activating Token Index: 354

Text #16

Max Range: 4.4958. Min Range: -4.4958

Max Act: 3.9604. Min Act: -0.1700

Data Index: 4959414 (Open Web Text)

Max Activating Token Index: 723

Text #17

Max Range: 4.4958. Min Range: -4.4958

Max Act: 3.9940. Min Act: -0.1700

Data Index: 1651091 (Open Web Text)

Max Activating Token Index: 160

Text #18

Max Range: 4.4958. Min Range: -4.4958

Max Act: 3.9954. Min Act: -0.1700

Data Index: 1459641 (Open Web Text)

Max Activating Token Index: 739

Text #19

Max Range: 4.4958. Min Range: -4.4958

Max Act: 3.9348. Min Act: -0.1700

Data Index: 6341303 (Open Web Text)

Max Activating Token Index: 393