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

Dataset: Open Web Text

Neuron 1205 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: 3.6167. Min Range: -3.6167

Max Act: 3.6167. Min Act: -0.1700

Data Index: 1406889 (Open Web Text)

Max Activating Token Index: 825

Text #1

Max Range: 3.6167. Min Range: -3.6167

Max Act: 3.5107. Min Act: -0.1700

Data Index: 3568830 (Open Web Text)

Max Activating Token Index: 474

Text #2

Max Range: 3.6167. Min Range: -3.6167

Max Act: 3.4500. Min Act: -0.1700

Data Index: 553890 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.6167. Min Range: -3.6167

Max Act: 3.4520. Min Act: -0.1700

Data Index: 487716 (Open Web Text)

Max Activating Token Index: 681

Text #4

Max Range: 3.6167. Min Range: -3.6167

Max Act: 3.4216. Min Act: -0.1700

Data Index: 373796 (Open Web Text)

Max Activating Token Index: 100

Text #5

Max Range: 3.6167. Min Range: -3.6167

Max Act: 3.3291. Min Act: -0.1700

Data Index: 2311677 (Open Web Text)

Max Activating Token Index: 795

Text #6

Max Range: 3.6167. Min Range: -3.6167

Max Act: 3.3160. Min Act: -0.1700

Data Index: 3233022 (Open Web Text)

Max Activating Token Index: 352

Text #7

Max Range: 3.6167. Min Range: -3.6167

Max Act: 3.3462. Min Act: -0.1700

Data Index: 2500093 (Open Web Text)

Max Activating Token Index: 852

Text #8

Max Range: 3.6167. Min Range: -3.6167

Max Act: 3.2835. Min Act: -0.1700

Data Index: 5348875 (Open Web Text)

Max Activating Token Index: 353

Text #9

Max Range: 3.6167. Min Range: -3.6167

Max Act: 3.3177. Min Act: -0.1700

Data Index: 6101476 (Open Web Text)

Max Activating Token Index: 527

Text #10

Max Range: 3.6167. Min Range: -3.6167

Max Act: 3.2818. Min Act: -0.1700

Data Index: 7992025 (Open Web Text)

Max Activating Token Index: 154

Text #11

Max Range: 3.6167. Min Range: -3.6167

Max Act: 3.2646. Min Act: -0.1700

Data Index: 2668277 (Open Web Text)

Max Activating Token Index: 303

Text #12

Max Range: 3.6167. Min Range: -3.6167

Max Act: 3.2210. Min Act: -0.1700

Data Index: 1356271 (Open Web Text)

Max Activating Token Index: 213

Text #13

Max Range: 3.6167. Min Range: -3.6167

Max Act: 3.2283. Min Act: -0.1700

Data Index: 419677 (Open Web Text)

Max Activating Token Index: 79

Text #14

Max Range: 3.6167. Min Range: -3.6167

Max Act: 3.2375. Min Act: -0.1700

Data Index: 2611741 (Open Web Text)

Max Activating Token Index: 526

Text #15

Max Range: 3.6167. Min Range: -3.6167

Max Act: 3.2248. Min Act: -0.1700

Data Index: 128107 (Open Web Text)

Max Activating Token Index: 17

Text #16

Max Range: 3.6167. Min Range: -3.6167

Max Act: 3.2212. Min Act: -0.1700

Data Index: 3000976 (Open Web Text)

Max Activating Token Index: 231

Text #17

Max Range: 3.6167. Min Range: -3.6167

Max Act: 3.2110. Min Act: -0.1700

Data Index: 1599337 (Open Web Text)

Max Activating Token Index: 463

Text #18

Max Range: 3.6167. Min Range: -3.6167

Max Act: 3.1941. Min Act: -0.1700

Data Index: 1233537 (Open Web Text)

Max Activating Token Index: 638

Text #19

Max Range: 3.6167. Min Range: -3.6167

Max Act: 3.2005. Min Act: -0.1700

Data Index: 4614467 (Open Web Text)

Max Activating Token Index: 931