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

Dataset: Open Web Text

Neuron 1167 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: 3.4965. Min Range: -3.4965

Max Act: 3.4965. Min Act: -0.1700

Data Index: 3447070 (Open Web Text)

Max Activating Token Index: 951

Text #1

Max Range: 3.4965. Min Range: -3.4965

Max Act: 3.4073. Min Act: -0.1700

Data Index: 7603959 (Open Web Text)

Max Activating Token Index: 910

Text #2

Max Range: 3.4965. Min Range: -3.4965

Max Act: 3.4561. Min Act: -0.1700

Data Index: 6648907 (Open Web Text)

Max Activating Token Index: 401

Text #3

Max Range: 3.4965. Min Range: -3.4965

Max Act: 3.4346. Min Act: -0.1700

Data Index: 3910984 (Open Web Text)

Max Activating Token Index: 250

Text #4

Max Range: 3.4965. Min Range: -3.4965

Max Act: 3.3963. Min Act: -0.1700

Data Index: 3244386 (Open Web Text)

Max Activating Token Index: 413

Text #5

Max Range: 3.4965. Min Range: -3.4965

Max Act: 3.3959. Min Act: -0.1700

Data Index: 3630881 (Open Web Text)

Max Activating Token Index: 460

Text #6

Max Range: 3.4965. Min Range: -3.4965

Max Act: 3.3650. Min Act: -0.1700

Data Index: 5655886 (Open Web Text)

Max Activating Token Index: 162

Text #7

Max Range: 3.4965. Min Range: -3.4965

Max Act: 3.3519. Min Act: -0.1700

Data Index: 6993799 (Open Web Text)

Max Activating Token Index: 943

Text #8

Max Range: 3.4965. Min Range: -3.4965

Max Act: 3.3617. Min Act: -0.1700

Data Index: 2339514 (Open Web Text)

Max Activating Token Index: 432

Text #9

Max Range: 3.4965. Min Range: -3.4965

Max Act: 3.3424. Min Act: -0.1700

Data Index: 7634924 (Open Web Text)

Max Activating Token Index: 993

Text #10

Max Range: 3.4965. Min Range: -3.4965

Max Act: 3.3238. Min Act: -0.1700

Data Index: 576777 (Open Web Text)

Max Activating Token Index: 427

Text #11

Max Range: 3.4965. Min Range: -3.4965

Max Act: 3.3639. Min Act: -0.1700

Data Index: 8261915 (Open Web Text)

Max Activating Token Index: 315

Text #12

Max Range: 3.4965. Min Range: -3.4965

Max Act: 3.2471. Min Act: -0.1700

Data Index: 2447652 (Open Web Text)

Max Activating Token Index: 500

Text #13

Max Range: 3.4965. Min Range: -3.4965

Max Act: 3.2457. Min Act: -0.1700

Data Index: 7272143 (Open Web Text)

Max Activating Token Index: 464

Text #14

Max Range: 3.4965. Min Range: -3.4965

Max Act: 3.2295. Min Act: -0.1700

Data Index: 7272152 (Open Web Text)

Max Activating Token Index: 909

Text #15

Max Range: 3.4965. Min Range: -3.4965

Max Act: 3.2376. Min Act: -0.1700

Data Index: 7093035 (Open Web Text)

Max Activating Token Index: 43

Text #16

Max Range: 3.4965. Min Range: -3.4965

Max Act: 3.2263. Min Act: -0.1700

Data Index: 8819154 (Open Web Text)

Max Activating Token Index: 943

Text #17

Max Range: 3.4965. Min Range: -3.4965

Max Act: 3.2304. Min Act: -0.1700

Data Index: 228920 (Open Web Text)

Max Activating Token Index: 737

Text #18

Max Range: 3.4965. Min Range: -3.4965

Max Act: 3.2357. Min Act: -0.1700

Data Index: 5004488 (Open Web Text)

Max Activating Token Index: 277

Text #19

Max Range: 3.4965. Min Range: -3.4965

Max Act: 3.2312. Min Act: -0.1700

Data Index: 3549894 (Open Web Text)

Max Activating Token Index: 558