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

Dataset: Open Web Text

Neuron 1166 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: 6.3167. Min Range: -6.3167

Max Act: 6.3167. Min Act: -0.1700

Data Index: 4265451 (Open Web Text)

Max Activating Token Index: 44

Text #1

Max Range: 6.3167. Min Range: -6.3167

Max Act: 6.2442. Min Act: -0.1700

Data Index: 2833859 (Open Web Text)

Max Activating Token Index: 343

Text #2

Max Range: 6.3167. Min Range: -6.3167

Max Act: 6.0786. Min Act: -0.1700

Data Index: 6906578 (Open Web Text)

Max Activating Token Index: 463

Text #3

Max Range: 6.3167. Min Range: -6.3167

Max Act: 6.0843. Min Act: -0.1700

Data Index: 5031950 (Open Web Text)

Max Activating Token Index: 134

Text #4

Max Range: 6.3167. Min Range: -6.3167

Max Act: 6.0230. Min Act: -0.1700

Data Index: 1379361 (Open Web Text)

Max Activating Token Index: 222

Text #5

Max Range: 6.3167. Min Range: -6.3167

Max Act: 5.9733. Min Act: -0.1700

Data Index: 6215136 (Open Web Text)

Max Activating Token Index: 211

Text #6

Max Range: 6.3167. Min Range: -6.3167

Max Act: 5.9679. Min Act: -0.1700

Data Index: 8311984 (Open Web Text)

Max Activating Token Index: 972

Text #7

Max Range: 6.3167. Min Range: -6.3167

Max Act: 5.9282. Min Act: -0.1700

Data Index: 2040455 (Open Web Text)

Max Activating Token Index: 358

Text #8

Max Range: 6.3167. Min Range: -6.3167

Max Act: 5.9394. Min Act: -0.1700

Data Index: 255518 (Open Web Text)

Max Activating Token Index: 563

Text #9

Max Range: 6.3167. Min Range: -6.3167

Max Act: 5.9228. Min Act: -0.1700

Data Index: 3761163 (Open Web Text)

Max Activating Token Index: 725

Text #10

Max Range: 6.3167. Min Range: -6.3167

Max Act: 5.9427. Min Act: -0.1700

Data Index: 6452922 (Open Web Text)

Max Activating Token Index: 748

Text #11

Max Range: 6.3167. Min Range: -6.3167

Max Act: 5.9362. Min Act: -0.1700

Data Index: 6459080 (Open Web Text)

Max Activating Token Index: 250

Text #12

Max Range: 6.3167. Min Range: -6.3167

Max Act: 5.8855. Min Act: -0.1700

Data Index: 2894807 (Open Web Text)

Max Activating Token Index: 632

Text #13

Max Range: 6.3167. Min Range: -6.3167

Max Act: 5.9223. Min Act: -0.1700

Data Index: 842958 (Open Web Text)

Max Activating Token Index: 395

Text #14

Max Range: 6.3167. Min Range: -6.3167

Max Act: 5.8910. Min Act: -0.1700

Data Index: 5301500 (Open Web Text)

Max Activating Token Index: 598

Text #15

Max Range: 6.3167. Min Range: -6.3167

Max Act: 5.9162. Min Act: -0.1700

Data Index: 3397944 (Open Web Text)

Max Activating Token Index: 1005

Text #16

Max Range: 6.3167. Min Range: -6.3167

Max Act: 5.9105. Min Act: -0.1700

Data Index: 2323090 (Open Web Text)

Max Activating Token Index: 22

Text #17

Max Range: 6.3167. Min Range: -6.3167

Max Act: 5.9174. Min Act: -0.1700

Data Index: 2386519 (Open Web Text)

Max Activating Token Index: 252

Text #18

Max Range: 6.3167. Min Range: -6.3167

Max Act: 5.9294. Min Act: -0.1700

Data Index: 4238170 (Open Web Text)

Max Activating Token Index: 373

Text #19

Max Range: 6.3167. Min Range: -6.3167

Max Act: 5.9249. Min Act: -0.1700

Data Index: 106107 (Open Web Text)

Max Activating Token Index: 870