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

Dataset: Open Web Text

Neuron 2117 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: 4.8206. Min Range: -4.8206

Max Act: 4.8206. Min Act: -0.1700

Data Index: 1899001 (Open Web Text)

Max Activating Token Index: 485

Text #1

Max Range: 4.8206. Min Range: -4.8206

Max Act: 4.7090. Min Act: -0.1700

Data Index: 5156763 (Open Web Text)

Max Activating Token Index: 425

Text #2

Max Range: 4.8206. Min Range: -4.8206

Max Act: 4.6501. Min Act: -0.1700

Data Index: 6344801 (Open Web Text)

Max Activating Token Index: 563

Text #3

Max Range: 4.8206. Min Range: -4.8206

Max Act: 4.7224. Min Act: -0.1700

Data Index: 1877087 (Open Web Text)

Max Activating Token Index: 683

Text #4

Max Range: 4.8206. Min Range: -4.8206

Max Act: 4.6963. Min Act: -0.1700

Data Index: 4166988 (Open Web Text)

Max Activating Token Index: 754

Text #5

Max Range: 4.8206. Min Range: -4.8206

Max Act: 4.6500. Min Act: -0.1700

Data Index: 921475 (Open Web Text)

Max Activating Token Index: 405

Text #6

Max Range: 4.8206. Min Range: -4.8206

Max Act: 4.6800. Min Act: -0.1700

Data Index: 2182904 (Open Web Text)

Max Activating Token Index: 674

Text #7

Max Range: 4.8206. Min Range: -4.8206

Max Act: 4.6973. Min Act: -0.1700

Data Index: 4096402 (Open Web Text)

Max Activating Token Index: 163

Text #8

Max Range: 4.8206. Min Range: -4.8206

Max Act: 4.7206. Min Act: -0.1700

Data Index: 4956534 (Open Web Text)

Max Activating Token Index: 996

Text #9

Max Range: 4.8206. Min Range: -4.8206

Max Act: 4.7044. Min Act: -0.1700

Data Index: 4956535 (Open Web Text)

Max Activating Token Index: 50

Text #10

Max Range: 4.8206. Min Range: -4.8206

Max Act: 4.6665. Min Act: -0.1700

Data Index: 301521 (Open Web Text)

Max Activating Token Index: 627

Text #11

Max Range: 4.8206. Min Range: -4.8206

Max Act: 4.6736. Min Act: -0.1700

Data Index: 2912322 (Open Web Text)

Max Activating Token Index: 355

Text #12

Max Range: 4.8206. Min Range: -4.8206

Max Act: 4.6494. Min Act: -0.1700

Data Index: 1958673 (Open Web Text)

Max Activating Token Index: 836

Text #13

Max Range: 4.8206. Min Range: -4.8206

Max Act: 4.5776. Min Act: -0.1700

Data Index: 724169 (Open Web Text)

Max Activating Token Index: 513

Text #14

Max Range: 4.8206. Min Range: -4.8206

Max Act: 4.5954. Min Act: -0.1700

Data Index: 7818203 (Open Web Text)

Max Activating Token Index: 720

Text #15

Max Range: 4.8206. Min Range: -4.8206

Max Act: 4.6567. Min Act: -0.1700

Data Index: 7402431 (Open Web Text)

Max Activating Token Index: 471

Text #16

Max Range: 4.8206. Min Range: -4.8206

Max Act: 4.6466. Min Act: -0.1700

Data Index: 6501334 (Open Web Text)

Max Activating Token Index: 399

Text #17

Max Range: 4.8206. Min Range: -4.8206

Max Act: 4.6407. Min Act: -0.1700

Data Index: 1109801 (Open Web Text)

Max Activating Token Index: 58

Text #18

Max Range: 4.8206. Min Range: -4.8206

Max Act: 4.6601. Min Act: -0.1700

Data Index: 1267433 (Open Web Text)

Max Activating Token Index: 431

Text #19

Max Range: 4.8206. Min Range: -4.8206

Max Act: 4.6433. Min Act: -0.1700

Data Index: 1545498 (Open Web Text)

Max Activating Token Index: 426