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

Dataset: Open Web Text

Neuron 2158 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: 3.1215. Min Range: -3.1215

Max Act: 3.1215. Min Act: -0.1700

Data Index: 7704284 (Open Web Text)

Max Activating Token Index: 1006

Text #1

Max Range: 3.1215. Min Range: -3.1215

Max Act: 3.1015. Min Act: -0.1700

Data Index: 8499707 (Open Web Text)

Max Activating Token Index: 472

Text #2

Max Range: 3.1215. Min Range: -3.1215

Max Act: 2.9949. Min Act: -0.1700

Data Index: 5644366 (Open Web Text)

Max Activating Token Index: 538

Text #3

Max Range: 3.1215. Min Range: -3.1215

Max Act: 2.9870. Min Act: -0.1700

Data Index: 980665 (Open Web Text)

Max Activating Token Index: 784

Text #4

Max Range: 3.1215. Min Range: -3.1215

Max Act: 2.9322. Min Act: -0.1700

Data Index: 7704283 (Open Web Text)

Max Activating Token Index: 483

Text #5

Max Range: 3.1215. Min Range: -3.1215

Max Act: 2.9539. Min Act: -0.1700

Data Index: 1987925 (Open Web Text)

Max Activating Token Index: 356

Text #6

Max Range: 3.1215. Min Range: -3.1215

Max Act: 2.9555. Min Act: -0.1700

Data Index: 5490925 (Open Web Text)

Max Activating Token Index: 252

Text #7

Max Range: 3.1215. Min Range: -3.1215

Max Act: 2.9563. Min Act: -0.1700

Data Index: 2233296 (Open Web Text)

Max Activating Token Index: 757

Text #8

Max Range: 3.1215. Min Range: -3.1215

Max Act: 2.9254. Min Act: -0.1700

Data Index: 3116541 (Open Web Text)

Max Activating Token Index: 240

Text #9

Max Range: 3.1215. Min Range: -3.1215

Max Act: 2.9324. Min Act: -0.1700

Data Index: 5451588 (Open Web Text)

Max Activating Token Index: 996

Text #10

Max Range: 3.1215. Min Range: -3.1215

Max Act: 2.9388. Min Act: -0.1700

Data Index: 628265 (Open Web Text)

Max Activating Token Index: 347

Text #11

Max Range: 3.1215. Min Range: -3.1215

Max Act: 2.9163. Min Act: -0.1700

Data Index: 2141137 (Open Web Text)

Max Activating Token Index: 643

Text #12

Max Range: 3.1215. Min Range: -3.1215

Max Act: 2.9065. Min Act: -0.1700

Data Index: 2344966 (Open Web Text)

Max Activating Token Index: 84

Text #13

Max Range: 3.1215. Min Range: -3.1215

Max Act: 2.9250. Min Act: -0.1700

Data Index: 6495196 (Open Web Text)

Max Activating Token Index: 277

Text #14

Max Range: 3.1215. Min Range: -3.1215

Max Act: 2.9195. Min Act: -0.1700

Data Index: 5260462 (Open Web Text)

Max Activating Token Index: 109

Text #15

Max Range: 3.1215. Min Range: -3.1215

Max Act: 2.9192. Min Act: -0.1700

Data Index: 5970506 (Open Web Text)

Max Activating Token Index: 968

Text #16

Max Range: 3.1215. Min Range: -3.1215

Max Act: 2.9042. Min Act: -0.1700

Data Index: 6719562 (Open Web Text)

Max Activating Token Index: 344

Text #17

Max Range: 3.1215. Min Range: -3.1215

Max Act: 2.9054. Min Act: -0.1700

Data Index: 6119554 (Open Web Text)

Max Activating Token Index: 291

Text #18

Max Range: 3.1215. Min Range: -3.1215

Max Act: 2.9116. Min Act: -0.1700

Data Index: 5783528 (Open Web Text)

Max Activating Token Index: 694

Text #19

Max Range: 3.1215. Min Range: -3.1215

Max Act: 2.9090. Min Act: -0.1700

Data Index: 5880850 (Open Web Text)

Max Activating Token Index: 163