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

Dataset: Open Web Text

Neuron 1071 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: 4.4417. Min Range: -4.4417

Max Act: 4.4314. Min Act: -0.1700

Data Index: 2422099 (Open Web Text)

Max Activating Token Index: 993

Text #1

Max Range: 4.4417. Min Range: -4.4417

Max Act: 4.4417. Min Act: -0.1700

Data Index: 1338563 (Open Web Text)

Max Activating Token Index: 904

Text #2

Max Range: 4.4417. Min Range: -4.4417

Max Act: 4.4016. Min Act: -0.1700

Data Index: 2840577 (Open Web Text)

Max Activating Token Index: 455

Text #3

Max Range: 4.4417. Min Range: -4.4417

Max Act: 4.3977. Min Act: -0.1700

Data Index: 3301522 (Open Web Text)

Max Activating Token Index: 425

Text #4

Max Range: 4.4417. Min Range: -4.4417

Max Act: 4.3839. Min Act: -0.1700

Data Index: 4145378 (Open Web Text)

Max Activating Token Index: 386

Text #5

Max Range: 4.4417. Min Range: -4.4417

Max Act: 4.4000. Min Act: -0.1700

Data Index: 532493 (Open Web Text)

Max Activating Token Index: 158

Text #6

Max Range: 4.4417. Min Range: -4.4417

Max Act: 4.3245. Min Act: -0.1700

Data Index: 4603253 (Open Web Text)

Max Activating Token Index: 146

Text #7

Max Range: 4.4417. Min Range: -4.4417

Max Act: 4.3580. Min Act: -0.1700

Data Index: 4071247 (Open Web Text)

Max Activating Token Index: 557

Text #8

Max Range: 4.4417. Min Range: -4.4417

Max Act: 4.3162. Min Act: -0.1700

Data Index: 6652433 (Open Web Text)

Max Activating Token Index: 652

Text #9

Max Range: 4.4417. Min Range: -4.4417

Max Act: 4.3417. Min Act: -0.1700

Data Index: 6429358 (Open Web Text)

Max Activating Token Index: 642

Text #10

Max Range: 4.4417. Min Range: -4.4417

Max Act: 4.3378. Min Act: -0.1700

Data Index: 6423180 (Open Web Text)

Max Activating Token Index: 228

Text #11

Max Range: 4.4417. Min Range: -4.4417

Max Act: 4.3542. Min Act: -0.1700

Data Index: 3361847 (Open Web Text)

Max Activating Token Index: 480

Text #12

Max Range: 4.4417. Min Range: -4.4417

Max Act: 4.3411. Min Act: -0.1700

Data Index: 4961897 (Open Web Text)

Max Activating Token Index: 19

Text #13

Max Range: 4.4417. Min Range: -4.4417

Max Act: 4.3624. Min Act: -0.1700

Data Index: 310448 (Open Web Text)

Max Activating Token Index: 15

Text #14

Max Range: 4.4417. Min Range: -4.4417

Max Act: 4.3350. Min Act: -0.1700

Data Index: 1514573 (Open Web Text)

Max Activating Token Index: 190

Text #15

Max Range: 4.4417. Min Range: -4.4417

Max Act: 4.3473. Min Act: -0.1700

Data Index: 609479 (Open Web Text)

Max Activating Token Index: 65

Text #16

Max Range: 4.4417. Min Range: -4.4417

Max Act: 4.3438. Min Act: -0.1700

Data Index: 2917908 (Open Web Text)

Max Activating Token Index: 124

Text #17

Max Range: 4.4417. Min Range: -4.4417

Max Act: 4.3479. Min Act: -0.1700

Data Index: 1312550 (Open Web Text)

Max Activating Token Index: 88

Text #18

Max Range: 4.4417. Min Range: -4.4417

Max Act: 4.3359. Min Act: -0.1700

Data Index: 4531065 (Open Web Text)

Max Activating Token Index: 234

Text #19

Max Range: 4.4417. Min Range: -4.4417

Max Act: 4.3224. Min Act: -0.1700

Data Index: 2185339 (Open Web Text)

Max Activating Token Index: 275