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

Dataset: Open Web Text

Neuron 1087 in Layer 0

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: 1.8700. Min Range: -1.8700

Max Act: 1.8700. Min Act: -0.1700

Data Index: 1384785 (Open Web Text)

Max Activating Token Index: 315

Text #1

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.7673. Min Act: -0.1700

Data Index: 6476256 (Open Web Text)

Max Activating Token Index: 673

Text #2

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.7570. Min Act: -0.1692

Data Index: 3350535 (Open Web Text)

Max Activating Token Index: 420

Text #3

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.7536. Min Act: -0.1699

Data Index: 7751839 (Open Web Text)

Max Activating Token Index: 380

Text #4

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.7579. Min Act: -0.1700

Data Index: 1726247 (Open Web Text)

Max Activating Token Index: 232

Text #5

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.7553. Min Act: -0.1688

Data Index: 2962461 (Open Web Text)

Max Activating Token Index: 648

Text #6

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.7483. Min Act: -0.1700

Data Index: 1230223 (Open Web Text)

Max Activating Token Index: 274

Text #7

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.7505. Min Act: -0.1700

Data Index: 8142576 (Open Web Text)

Max Activating Token Index: 279

Text #8

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.7476. Min Act: -0.1699

Data Index: 2516261 (Open Web Text)

Max Activating Token Index: 236

Text #9

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.7532. Min Act: -0.1681

Data Index: 148718 (Open Web Text)

Max Activating Token Index: 930

Text #10

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.7452. Min Act: -0.1700

Data Index: 8351254 (Open Web Text)

Max Activating Token Index: 983

Text #11

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.7350. Min Act: -0.1700

Data Index: 832043 (Open Web Text)

Max Activating Token Index: 317

Text #12

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.7271. Min Act: -0.1652

Data Index: 370361 (Open Web Text)

Max Activating Token Index: 435

Text #13

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.7223. Min Act: -0.1700

Data Index: 8828298 (Open Web Text)

Max Activating Token Index: 91

Text #14

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.7235. Min Act: -0.1699

Data Index: 5864210 (Open Web Text)

Max Activating Token Index: 739

Text #15

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.7124. Min Act: -0.1700

Data Index: 2911248 (Open Web Text)

Max Activating Token Index: 189

Text #16

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.7150. Min Act: -0.1700

Data Index: 3071691 (Open Web Text)

Max Activating Token Index: 975

Text #17

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.7060. Min Act: -0.1700

Data Index: 2353452 (Open Web Text)

Max Activating Token Index: 567

Text #18

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.7173. Min Act: -0.1700

Data Index: 379218 (Open Web Text)

Max Activating Token Index: 171

Text #19

Max Range: 1.8700. Min Range: -1.8700

Max Act: 1.7079. Min Act: -0.1700

Data Index: 3725343 (Open Web Text)

Max Activating Token Index: 351