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

Dataset: Open Web Text

Neuron 840 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: 4.0380. Min Range: -4.0380

Max Act: 4.0380. Min Act: -0.1700

Data Index: 7955473 (Open Web Text)

Max Activating Token Index: 81

Text #1

Max Range: 4.0380. Min Range: -4.0380

Max Act: 4.0027. Min Act: -0.1700

Data Index: 5048152 (Open Web Text)

Max Activating Token Index: 176

Text #2

Max Range: 4.0380. Min Range: -4.0380

Max Act: 3.9420. Min Act: -0.1700

Data Index: 4462608 (Open Web Text)

Max Activating Token Index: 254

Text #3

Max Range: 4.0380. Min Range: -4.0380

Max Act: 3.9519. Min Act: -0.1700

Data Index: 7062074 (Open Web Text)

Max Activating Token Index: 151

Text #4

Max Range: 4.0380. Min Range: -4.0380

Max Act: 3.9661. Min Act: -0.1700

Data Index: 5529471 (Open Web Text)

Max Activating Token Index: 203

Text #5

Max Range: 4.0380. Min Range: -4.0380

Max Act: 3.9441. Min Act: -0.1700

Data Index: 6455239 (Open Web Text)

Max Activating Token Index: 486

Text #6

Max Range: 4.0380. Min Range: -4.0380

Max Act: 3.9520. Min Act: -0.1700

Data Index: 5809268 (Open Web Text)

Max Activating Token Index: 583

Text #7

Max Range: 4.0380. Min Range: -4.0380

Max Act: 3.9379. Min Act: -0.1700

Data Index: 6388971 (Open Web Text)

Max Activating Token Index: 531

Text #8

Max Range: 4.0380. Min Range: -4.0380

Max Act: 3.9262. Min Act: -0.1700

Data Index: 968138 (Open Web Text)

Max Activating Token Index: 548

Text #9

Max Range: 4.0380. Min Range: -4.0380

Max Act: 3.9249. Min Act: -0.1700

Data Index: 6451158 (Open Web Text)

Max Activating Token Index: 84

Text #10

Max Range: 4.0380. Min Range: -4.0380

Max Act: 3.9215. Min Act: -0.1700

Data Index: 7841068 (Open Web Text)

Max Activating Token Index: 484

Text #11

Max Range: 4.0380. Min Range: -4.0380

Max Act: 3.9233. Min Act: -0.1700

Data Index: 6107934 (Open Web Text)

Max Activating Token Index: 85

Text #12

Max Range: 4.0380. Min Range: -4.0380

Max Act: 3.9321. Min Act: -0.1700

Data Index: 5796298 (Open Web Text)

Max Activating Token Index: 250

Text #13

Max Range: 4.0380. Min Range: -4.0380

Max Act: 3.9213. Min Act: -0.1700

Data Index: 1291450 (Open Web Text)

Max Activating Token Index: 69

Text #14

Max Range: 4.0380. Min Range: -4.0380

Max Act: 3.9241. Min Act: -0.1700

Data Index: 3741065 (Open Web Text)

Max Activating Token Index: 251

Text #15

Max Range: 4.0380. Min Range: -4.0380

Max Act: 3.8792. Min Act: -0.1700

Data Index: 6424586 (Open Web Text)

Max Activating Token Index: 466

Text #16

Max Range: 4.0380. Min Range: -4.0380

Max Act: 3.8930. Min Act: -0.1700

Data Index: 5202145 (Open Web Text)

Max Activating Token Index: 723

Text #17

Max Range: 4.0380. Min Range: -4.0380

Max Act: 3.9006. Min Act: -0.1700

Data Index: 6607054 (Open Web Text)

Max Activating Token Index: 422

Text #18

Max Range: 4.0380. Min Range: -4.0380

Max Act: 3.8791. Min Act: -0.1700

Data Index: 866086 (Open Web Text)

Max Activating Token Index: 458

Text #19

Max Range: 4.0380. Min Range: -4.0380

Max Act: 3.9002. Min Act: -0.1700

Data Index: 7090143 (Open Web Text)

Max Activating Token Index: 78