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

Dataset: Open Web Text

Neuron 2570 in Layer 6

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: 2.7696. Min Range: -2.7696

Max Act: 2.7696. Min Act: -0.1700

Data Index: 7722209 (Open Web Text)

Max Activating Token Index: 55

Text #1

Max Range: 2.7696. Min Range: -2.7696

Max Act: 2.7003. Min Act: -0.1700

Data Index: 7984882 (Open Web Text)

Max Activating Token Index: 325

Text #2

Max Range: 2.7696. Min Range: -2.7696

Max Act: 2.6972. Min Act: -0.1700

Data Index: 6525180 (Open Web Text)

Max Activating Token Index: 497

Text #3

Max Range: 2.7696. Min Range: -2.7696

Max Act: 2.6784. Min Act: -0.1700

Data Index: 3024305 (Open Web Text)

Max Activating Token Index: 320

Text #4

Max Range: 2.7696. Min Range: -2.7696

Max Act: 2.6929. Min Act: -0.1700

Data Index: 3461261 (Open Web Text)

Max Activating Token Index: 768

Text #5

Max Range: 2.7696. Min Range: -2.7696

Max Act: 2.5922. Min Act: -0.1700

Data Index: 2739499 (Open Web Text)

Max Activating Token Index: 642

Text #6

Max Range: 2.7696. Min Range: -2.7696

Max Act: 2.6211. Min Act: -0.1700

Data Index: 244872 (Open Web Text)

Max Activating Token Index: 574

Text #7

Max Range: 2.7696. Min Range: -2.7696

Max Act: 2.5905. Min Act: -0.1700

Data Index: 2583088 (Open Web Text)

Max Activating Token Index: 753

Text #8

Max Range: 2.7696. Min Range: -2.7696

Max Act: 2.5778. Min Act: -0.1700

Data Index: 3140502 (Open Web Text)

Max Activating Token Index: 929

Text #9

Max Range: 2.7696. Min Range: -2.7696

Max Act: 2.5734. Min Act: -0.1700

Data Index: 5437185 (Open Web Text)

Max Activating Token Index: 260

Text #10

Max Range: 2.7696. Min Range: -2.7696

Max Act: 2.5628. Min Act: -0.1700

Data Index: 6154347 (Open Web Text)

Max Activating Token Index: 744

Text #11

Max Range: 2.7696. Min Range: -2.7696

Max Act: 2.5584. Min Act: -0.1700

Data Index: 1358529 (Open Web Text)

Max Activating Token Index: 279

Text #12

Max Range: 2.7696. Min Range: -2.7696

Max Act: 2.5479. Min Act: -0.1700

Data Index: 6899533 (Open Web Text)

Max Activating Token Index: 97

Text #13

Max Range: 2.7696. Min Range: -2.7696

Max Act: 2.5409. Min Act: -0.1700

Data Index: 5721634 (Open Web Text)

Max Activating Token Index: 687

Text #14

Max Range: 2.7696. Min Range: -2.7696

Max Act: 2.5429. Min Act: -0.1700

Data Index: 7600121 (Open Web Text)

Max Activating Token Index: 206

Text #15

Max Range: 2.7696. Min Range: -2.7696

Max Act: 2.5448. Min Act: -0.1700

Data Index: 3727821 (Open Web Text)

Max Activating Token Index: 964

Text #16

Max Range: 2.7696. Min Range: -2.7696

Max Act: 2.5447. Min Act: -0.1700

Data Index: 8717376 (Open Web Text)

Max Activating Token Index: 433

Text #17

Max Range: 2.7696. Min Range: -2.7696

Max Act: 2.5466. Min Act: -0.1700

Data Index: 3903366 (Open Web Text)

Max Activating Token Index: 191

Text #18

Max Range: 2.7696. Min Range: -2.7696

Max Act: 2.5316. Min Act: -0.1700

Data Index: 7756314 (Open Web Text)

Max Activating Token Index: 352

Text #19

Max Range: 2.7696. Min Range: -2.7696

Max Act: 2.5082. Min Act: -0.1700

Data Index: 6878134 (Open Web Text)

Max Activating Token Index: 614