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

Dataset: Open Web Text

Neuron 1936 in Layer 1

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: 3.4554. Min Range: -3.4554

Max Act: 3.4554. Min Act: -0.1700

Data Index: 1115921 (Open Web Text)

Max Activating Token Index: 417

Text #1

Max Range: 3.4554. Min Range: -3.4554

Max Act: 3.4149. Min Act: -0.1700

Data Index: 2514452 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 3.4554. Min Range: -3.4554

Max Act: 3.3848. Min Act: -0.1700

Data Index: 1115926 (Open Web Text)

Max Activating Token Index: 545

Text #3

Max Range: 3.4554. Min Range: -3.4554

Max Act: 3.3617. Min Act: -0.1700

Data Index: 1115928 (Open Web Text)

Max Activating Token Index: 285

Text #4

Max Range: 3.4554. Min Range: -3.4554

Max Act: 3.3607. Min Act: -0.1700

Data Index: 1115916 (Open Web Text)

Max Activating Token Index: 347

Text #5

Max Range: 3.4554. Min Range: -3.4554

Max Act: 3.3315. Min Act: -0.1700

Data Index: 1115917 (Open Web Text)

Max Activating Token Index: 299

Text #6

Max Range: 3.4554. Min Range: -3.4554

Max Act: 3.3499. Min Act: -0.1700

Data Index: 1115922 (Open Web Text)

Max Activating Token Index: 333

Text #7

Max Range: 3.4554. Min Range: -3.4554

Max Act: 3.3315. Min Act: -0.1700

Data Index: 1115941 (Open Web Text)

Max Activating Token Index: 421

Text #8

Max Range: 3.4554. Min Range: -3.4554

Max Act: 3.3268. Min Act: -0.1700

Data Index: 1115953 (Open Web Text)

Max Activating Token Index: 281

Text #9

Max Range: 3.4554. Min Range: -3.4554

Max Act: 3.3098. Min Act: -0.1700

Data Index: 1203273 (Open Web Text)

Max Activating Token Index: 726

Text #10

Max Range: 3.4554. Min Range: -3.4554

Max Act: 3.2983. Min Act: -0.1700

Data Index: 1203257 (Open Web Text)

Max Activating Token Index: 141

Text #11

Max Range: 3.4554. Min Range: -3.4554

Max Act: 3.2847. Min Act: -0.1700

Data Index: 2917623 (Open Web Text)

Max Activating Token Index: 569

Text #12

Max Range: 3.4554. Min Range: -3.4554

Max Act: 3.2757. Min Act: -0.1700

Data Index: 1115929 (Open Web Text)

Max Activating Token Index: 140

Text #13

Max Range: 3.4554. Min Range: -3.4554

Max Act: 3.2774. Min Act: -0.1700

Data Index: 1203262 (Open Web Text)

Max Activating Token Index: 548

Text #14

Max Range: 3.4554. Min Range: -3.4554

Max Act: 3.2818. Min Act: -0.1700

Data Index: 1115936 (Open Web Text)

Max Activating Token Index: 226

Text #15

Max Range: 3.4554. Min Range: -3.4554

Max Act: 3.2389. Min Act: -0.1700

Data Index: 1203256 (Open Web Text)

Max Activating Token Index: 507

Text #16

Max Range: 3.4554. Min Range: -3.4554

Max Act: 3.2177. Min Act: -0.1700

Data Index: 1115932 (Open Web Text)

Max Activating Token Index: 74

Text #17

Max Range: 3.4554. Min Range: -3.4554

Max Act: 3.2291. Min Act: -0.1700

Data Index: 1203271 (Open Web Text)

Max Activating Token Index: 687

Text #18

Max Range: 3.4554. Min Range: -3.4554

Max Act: 3.2297. Min Act: -0.1700

Data Index: 1115946 (Open Web Text)

Max Activating Token Index: 69

Text #19

Max Range: 3.4554. Min Range: -3.4554

Max Act: 3.2436. Min Act: -0.1700

Data Index: 1115951 (Open Web Text)

Max Activating Token Index: 277