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

Dataset: Open Web Text

Neuron 1567 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: 3.9375. Min Range: -3.9375

Max Act: 3.9375. Min Act: -0.1700

Data Index: 2974588 (Open Web Text)

Max Activating Token Index: 914

Text #1

Max Range: 3.9375. Min Range: -3.9375

Max Act: 3.8418. Min Act: -0.1700

Data Index: 473677 (Open Web Text)

Max Activating Token Index: 524

Text #2

Max Range: 3.9375. Min Range: -3.9375

Max Act: 3.8908. Min Act: -0.1700

Data Index: 4955774 (Open Web Text)

Max Activating Token Index: 107

Text #3

Max Range: 3.9375. Min Range: -3.9375

Max Act: 3.8359. Min Act: -0.1700

Data Index: 5788407 (Open Web Text)

Max Activating Token Index: 455

Text #4

Max Range: 3.9375. Min Range: -3.9375

Max Act: 3.8328. Min Act: -0.1700

Data Index: 8800588 (Open Web Text)

Max Activating Token Index: 644

Text #5

Max Range: 3.9375. Min Range: -3.9375

Max Act: 3.7787. Min Act: -0.1700

Data Index: 8800346 (Open Web Text)

Max Activating Token Index: 601

Text #6

Max Range: 3.9375. Min Range: -3.9375

Max Act: 3.8075. Min Act: -0.1700

Data Index: 7406423 (Open Web Text)

Max Activating Token Index: 100

Text #7

Max Range: 3.9375. Min Range: -3.9375

Max Act: 3.7885. Min Act: -0.1700

Data Index: 8623795 (Open Web Text)

Max Activating Token Index: 127

Text #8

Max Range: 3.9375. Min Range: -3.9375

Max Act: 3.8078. Min Act: -0.1700

Data Index: 3456807 (Open Web Text)

Max Activating Token Index: 805

Text #9

Max Range: 3.9375. Min Range: -3.9375

Max Act: 3.7488. Min Act: -0.1700

Data Index: 123935 (Open Web Text)

Max Activating Token Index: 880

Text #10

Max Range: 3.9375. Min Range: -3.9375

Max Act: 3.7991. Min Act: -0.1700

Data Index: 7594639 (Open Web Text)

Max Activating Token Index: 609

Text #11

Max Range: 3.9375. Min Range: -3.9375

Max Act: 3.7873. Min Act: -0.1700

Data Index: 8623794 (Open Web Text)

Max Activating Token Index: 482

Text #12

Max Range: 3.9375. Min Range: -3.9375

Max Act: 3.7485. Min Act: -0.1700

Data Index: 6931715 (Open Web Text)

Max Activating Token Index: 957

Text #13

Max Range: 3.9375. Min Range: -3.9375

Max Act: 3.7403. Min Act: -0.1700

Data Index: 6220949 (Open Web Text)

Max Activating Token Index: 949

Text #14

Max Range: 3.9375. Min Range: -3.9375

Max Act: 3.7321. Min Act: -0.1700

Data Index: 3642874 (Open Web Text)

Max Activating Token Index: 784

Text #15

Max Range: 3.9375. Min Range: -3.9375

Max Act: 3.7253. Min Act: -0.1700

Data Index: 7349438 (Open Web Text)

Max Activating Token Index: 294

Text #16

Max Range: 3.9375. Min Range: -3.9375

Max Act: 3.7217. Min Act: -0.1700

Data Index: 633389 (Open Web Text)

Max Activating Token Index: 193

Text #17

Max Range: 3.9375. Min Range: -3.9375

Max Act: 3.7417. Min Act: -0.1700

Data Index: 3293564 (Open Web Text)

Max Activating Token Index: 478

Text #18

Max Range: 3.9375. Min Range: -3.9375

Max Act: 3.7492. Min Act: -0.1700

Data Index: 2604459 (Open Web Text)

Max Activating Token Index: 1022

Text #19

Max Range: 3.9375. Min Range: -3.9375

Max Act: 3.7113. Min Act: -0.1700

Data Index: 6525278 (Open Web Text)

Max Activating Token Index: 509