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

Dataset: Open Web Text

Neuron 26 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: 1.8099. Min Range: -1.8099

Max Act: 1.8099. Min Act: -0.0527

Data Index: 3053667 (Open Web Text)

Max Activating Token Index: 400

Text #1

Max Range: 1.8099. Min Range: -1.8099

Max Act: 1.8042. Min Act: -0.0884

Data Index: 3555328 (Open Web Text)

Max Activating Token Index: 674

Text #2

Max Range: 1.8099. Min Range: -1.8099

Max Act: 1.7792. Min Act: -0.0538

Data Index: 5026271 (Open Web Text)

Max Activating Token Index: 616

Text #3

Max Range: 1.8099. Min Range: -1.8099

Max Act: 1.7822. Min Act: -0.0537

Data Index: 22608 (Open Web Text)

Max Activating Token Index: 806

Text #4

Max Range: 1.8099. Min Range: -1.8099

Max Act: 1.7691. Min Act: -0.1142

Data Index: 2576376 (Open Web Text)

Max Activating Token Index: 777

Text #5

Max Range: 1.8099. Min Range: -1.8099

Max Act: 1.7617. Min Act: -0.0590

Data Index: 598345 (Open Web Text)

Max Activating Token Index: 131

Text #6

Max Range: 1.8099. Min Range: -1.8099

Max Act: 1.7587. Min Act: -0.1202

Data Index: 1122645 (Open Web Text)

Max Activating Token Index: 858

Text #7

Max Range: 1.8099. Min Range: -1.8099

Max Act: 1.7590. Min Act: -0.0495

Data Index: 8132199 (Open Web Text)

Max Activating Token Index: 241

Text #8

Max Range: 1.8099. Min Range: -1.8099

Max Act: 1.7349. Min Act: -0.0774

Data Index: 982111 (Open Web Text)

Max Activating Token Index: 336

Text #9

Max Range: 1.8099. Min Range: -1.8099

Max Act: 1.7424. Min Act: -0.0662

Data Index: 2895865 (Open Web Text)

Max Activating Token Index: 876

Text #10

Max Range: 1.8099. Min Range: -1.8099

Max Act: 1.7368. Min Act: -0.1048

Data Index: 7212243 (Open Web Text)

Max Activating Token Index: 694

Text #11

Max Range: 1.8099. Min Range: -1.8099

Max Act: 1.7207. Min Act: -0.0750

Data Index: 3553902 (Open Web Text)

Max Activating Token Index: 802

Text #12

Max Range: 1.8099. Min Range: -1.8099

Max Act: 1.7339. Min Act: -0.1167

Data Index: 6526002 (Open Web Text)

Max Activating Token Index: 807

Text #13

Max Range: 1.8099. Min Range: -1.8099

Max Act: 1.7310. Min Act: -0.1007

Data Index: 1657329 (Open Web Text)

Max Activating Token Index: 232

Text #14

Max Range: 1.8099. Min Range: -1.8099

Max Act: 1.7248. Min Act: -0.0680

Data Index: 1319923 (Open Web Text)

Max Activating Token Index: 629

Text #15

Max Range: 1.8099. Min Range: -1.8099

Max Act: 1.7072. Min Act: -0.0875

Data Index: 7646206 (Open Web Text)

Max Activating Token Index: 593

Text #16

Max Range: 1.8099. Min Range: -1.8099

Max Act: 1.7188. Min Act: -0.0579

Data Index: 722165 (Open Web Text)

Max Activating Token Index: 552

Text #17

Max Range: 1.8099. Min Range: -1.8099

Max Act: 1.6963. Min Act: -0.1098

Data Index: 5425602 (Open Web Text)

Max Activating Token Index: 718

Text #18

Max Range: 1.8099. Min Range: -1.8099

Max Act: 1.7066. Min Act: -0.0974

Data Index: 5460685 (Open Web Text)

Max Activating Token Index: 415

Text #19

Max Range: 1.8099. Min Range: -1.8099

Max Act: 1.7034. Min Act: -0.0746

Data Index: 2899763 (Open Web Text)

Max Activating Token Index: 842