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

Dataset: Open Web Text

Neuron 984 in Layer 2

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: 4.3415. Min Range: -4.3415

Max Act: 4.3238. Min Act: -0.1700

Data Index: 5020196 (Open Web Text)

Max Activating Token Index: 573

Text #1

Max Range: 4.3415. Min Range: -4.3415

Max Act: 4.3415. Min Act: -0.1700

Data Index: 8264225 (Open Web Text)

Max Activating Token Index: 700

Text #2

Max Range: 4.3415. Min Range: -4.3415

Max Act: 4.2772. Min Act: -0.1700

Data Index: 2332370 (Open Web Text)

Max Activating Token Index: 963

Text #3

Max Range: 4.3415. Min Range: -4.3415

Max Act: 4.2555. Min Act: -0.1700

Data Index: 1508019 (Open Web Text)

Max Activating Token Index: 425

Text #4

Max Range: 4.3415. Min Range: -4.3415

Max Act: 4.2450. Min Act: -0.1700

Data Index: 5529935 (Open Web Text)

Max Activating Token Index: 81

Text #5

Max Range: 4.3415. Min Range: -4.3415

Max Act: 4.2896. Min Act: -0.1700

Data Index: 6614592 (Open Web Text)

Max Activating Token Index: 573

Text #6

Max Range: 4.3415. Min Range: -4.3415

Max Act: 4.2883. Min Act: -0.1700

Data Index: 6646259 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 4.3415. Min Range: -4.3415

Max Act: 4.2619. Min Act: -0.1700

Data Index: 6764824 (Open Web Text)

Max Activating Token Index: 87

Text #8

Max Range: 4.3415. Min Range: -4.3415

Max Act: 4.2578. Min Act: -0.1700

Data Index: 4812634 (Open Web Text)

Max Activating Token Index: 103

Text #9

Max Range: 4.3415. Min Range: -4.3415

Max Act: 4.2575. Min Act: -0.1700

Data Index: 187765 (Open Web Text)

Max Activating Token Index: 356

Text #10

Max Range: 4.3415. Min Range: -4.3415

Max Act: 4.2235. Min Act: -0.1700

Data Index: 8514245 (Open Web Text)

Max Activating Token Index: 171

Text #11

Max Range: 4.3415. Min Range: -4.3415

Max Act: 4.2301. Min Act: -0.1700

Data Index: 7765441 (Open Web Text)

Max Activating Token Index: 83

Text #12

Max Range: 4.3415. Min Range: -4.3415

Max Act: 4.2544. Min Act: -0.1700

Data Index: 7555616 (Open Web Text)

Max Activating Token Index: 89

Text #13

Max Range: 4.3415. Min Range: -4.3415

Max Act: 4.2337. Min Act: -0.1700

Data Index: 1473678 (Open Web Text)

Max Activating Token Index: 136

Text #14

Max Range: 4.3415. Min Range: -4.3415

Max Act: 4.2364. Min Act: -0.1700

Data Index: 3504770 (Open Web Text)

Max Activating Token Index: 98

Text #15

Max Range: 4.3415. Min Range: -4.3415

Max Act: 4.2269. Min Act: -0.1700

Data Index: 2142406 (Open Web Text)

Max Activating Token Index: 442

Text #16

Max Range: 4.3415. Min Range: -4.3415

Max Act: 4.2562. Min Act: -0.1700

Data Index: 6582548 (Open Web Text)

Max Activating Token Index: 73

Text #17

Max Range: 4.3415. Min Range: -4.3415

Max Act: 4.2384. Min Act: -0.1700

Data Index: 3229443 (Open Web Text)

Max Activating Token Index: 343

Text #18

Max Range: 4.3415. Min Range: -4.3415

Max Act: 4.1806. Min Act: -0.1700

Data Index: 2280217 (Open Web Text)

Max Activating Token Index: 893

Text #19

Max Range: 4.3415. Min Range: -4.3415

Max Act: 4.1959. Min Act: -0.1700

Data Index: 1202695 (Open Web Text)

Max Activating Token Index: 78