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

Dataset: Open Web Text

Neuron 999 in Layer 4

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: 4.6383. Min Range: -4.6383

Max Act: 4.6061. Min Act: -0.1700

Data Index: 2917047 (Open Web Text)

Max Activating Token Index: 144

Text #1

Max Range: 4.6383. Min Range: -4.6383

Max Act: 4.6172. Min Act: -0.1700

Data Index: 735450 (Open Web Text)

Max Activating Token Index: 741

Text #2

Max Range: 4.6383. Min Range: -4.6383

Max Act: 4.6316. Min Act: -0.1700

Data Index: 7188320 (Open Web Text)

Max Activating Token Index: 37

Text #3

Max Range: 4.6383. Min Range: -4.6383

Max Act: 4.6383. Min Act: -0.1700

Data Index: 2018624 (Open Web Text)

Max Activating Token Index: 251

Text #4

Max Range: 4.6383. Min Range: -4.6383

Max Act: 4.5725. Min Act: -0.1700

Data Index: 4455857 (Open Web Text)

Max Activating Token Index: 1020

Text #5

Max Range: 4.6383. Min Range: -4.6383

Max Act: 4.5301. Min Act: -0.1700

Data Index: 6560980 (Open Web Text)

Max Activating Token Index: 146

Text #6

Max Range: 4.6383. Min Range: -4.6383

Max Act: 4.4976. Min Act: -0.1700

Data Index: 4689281 (Open Web Text)

Max Activating Token Index: 828

Text #7

Max Range: 4.6383. Min Range: -4.6383

Max Act: 4.4855. Min Act: -0.1700

Data Index: 975102 (Open Web Text)

Max Activating Token Index: 877

Text #8

Max Range: 4.6383. Min Range: -4.6383

Max Act: 4.5133. Min Act: -0.1700

Data Index: 487375 (Open Web Text)

Max Activating Token Index: 705

Text #9

Max Range: 4.6383. Min Range: -4.6383

Max Act: 4.4657. Min Act: -0.1700

Data Index: 1467667 (Open Web Text)

Max Activating Token Index: 652

Text #10

Max Range: 4.6383. Min Range: -4.6383

Max Act: 4.5044. Min Act: -0.1700

Data Index: 4254222 (Open Web Text)

Max Activating Token Index: 252

Text #11

Max Range: 4.6383. Min Range: -4.6383

Max Act: 4.4343. Min Act: -0.1700

Data Index: 3537012 (Open Web Text)

Max Activating Token Index: 475

Text #12

Max Range: 4.6383. Min Range: -4.6383

Max Act: 4.4426. Min Act: -0.1700

Data Index: 3542703 (Open Web Text)

Max Activating Token Index: 1015

Text #13

Max Range: 4.6383. Min Range: -4.6383

Max Act: 4.4688. Min Act: -0.1700

Data Index: 963703 (Open Web Text)

Max Activating Token Index: 98

Text #14

Max Range: 4.6383. Min Range: -4.6383

Max Act: 4.4428. Min Act: -0.1700

Data Index: 6367751 (Open Web Text)

Max Activating Token Index: 10

Text #15

Max Range: 4.6383. Min Range: -4.6383

Max Act: 4.4336. Min Act: -0.1700

Data Index: 3663352 (Open Web Text)

Max Activating Token Index: 66

Text #16

Max Range: 4.6383. Min Range: -4.6383

Max Act: 4.4103. Min Act: -0.1700

Data Index: 1983377 (Open Web Text)

Max Activating Token Index: 190

Text #17

Max Range: 4.6383. Min Range: -4.6383

Max Act: 4.4084. Min Act: -0.1700

Data Index: 4987299 (Open Web Text)

Max Activating Token Index: 644

Text #18

Max Range: 4.6383. Min Range: -4.6383

Max Act: 4.3869. Min Act: -0.1700

Data Index: 4209875 (Open Web Text)

Max Activating Token Index: 148

Text #19

Max Range: 4.6383. Min Range: -4.6383

Max Act: 4.4257. Min Act: -0.1700

Data Index: 6633404 (Open Web Text)

Max Activating Token Index: 74