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

Dataset: Open Web Text

Neuron 685 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: 5.9308. Min Range: -5.9308

Max Act: 5.9308. Min Act: -0.1700

Data Index: 6326752 (Open Web Text)

Max Activating Token Index: 412

Text #1

Max Range: 5.9308. Min Range: -5.9308

Max Act: 5.8394. Min Act: -0.1700

Data Index: 2541111 (Open Web Text)

Max Activating Token Index: 427

Text #2

Max Range: 5.9308. Min Range: -5.9308

Max Act: 5.8552. Min Act: -0.1700

Data Index: 1495275 (Open Web Text)

Max Activating Token Index: 966

Text #3

Max Range: 5.9308. Min Range: -5.9308

Max Act: 5.8263. Min Act: -0.1700

Data Index: 1786059 (Open Web Text)

Max Activating Token Index: 415

Text #4

Max Range: 5.9308. Min Range: -5.9308

Max Act: 5.8330. Min Act: -0.1700

Data Index: 5729064 (Open Web Text)

Max Activating Token Index: 986

Text #5

Max Range: 5.9308. Min Range: -5.9308

Max Act: 5.7501. Min Act: -0.1700

Data Index: 6515159 (Open Web Text)

Max Activating Token Index: 979

Text #6

Max Range: 5.9308. Min Range: -5.9308

Max Act: 5.8333. Min Act: -0.1700

Data Index: 1459284 (Open Web Text)

Max Activating Token Index: 947

Text #7

Max Range: 5.9308. Min Range: -5.9308

Max Act: 5.7185. Min Act: -0.1700

Data Index: 4766356 (Open Web Text)

Max Activating Token Index: 510

Text #8

Max Range: 5.9308. Min Range: -5.9308

Max Act: 5.7238. Min Act: -0.1700

Data Index: 4341504 (Open Web Text)

Max Activating Token Index: 590

Text #9

Max Range: 5.9308. Min Range: -5.9308

Max Act: 5.6867. Min Act: -0.1700

Data Index: 7381456 (Open Web Text)

Max Activating Token Index: 448

Text #10

Max Range: 5.9308. Min Range: -5.9308

Max Act: 5.6604. Min Act: -0.1700

Data Index: 6758570 (Open Web Text)

Max Activating Token Index: 254

Text #11

Max Range: 5.9308. Min Range: -5.9308

Max Act: 5.6708. Min Act: -0.1700

Data Index: 7919089 (Open Web Text)

Max Activating Token Index: 975

Text #12

Max Range: 5.9308. Min Range: -5.9308

Max Act: 5.6531. Min Act: -0.1700

Data Index: 708820 (Open Web Text)

Max Activating Token Index: 756

Text #13

Max Range: 5.9308. Min Range: -5.9308

Max Act: 5.6951. Min Act: -0.1700

Data Index: 2128604 (Open Web Text)

Max Activating Token Index: 735

Text #14

Max Range: 5.9308. Min Range: -5.9308

Max Act: 5.6041. Min Act: -0.1700

Data Index: 1124683 (Open Web Text)

Max Activating Token Index: 651

Text #15

Max Range: 5.9308. Min Range: -5.9308

Max Act: 5.5583. Min Act: -0.1700

Data Index: 3833023 (Open Web Text)

Max Activating Token Index: 289

Text #16

Max Range: 5.9308. Min Range: -5.9308

Max Act: 5.5459. Min Act: -0.1700

Data Index: 3191698 (Open Web Text)

Max Activating Token Index: 682

Text #17

Max Range: 5.9308. Min Range: -5.9308

Max Act: 5.5245. Min Act: -0.1700

Data Index: 4844392 (Open Web Text)

Max Activating Token Index: 336

Text #18

Max Range: 5.9308. Min Range: -5.9308

Max Act: 5.5338. Min Act: -0.1700

Data Index: 757923 (Open Web Text)

Max Activating Token Index: 45

Text #19

Max Range: 5.9308. Min Range: -5.9308

Max Act: 5.5195. Min Act: -0.1700

Data Index: 2165507 (Open Web Text)

Max Activating Token Index: 987