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

Dataset: Open Web Text

Neuron 258 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: 5.6983. Min Range: -5.6983

Max Act: 5.6983. Min Act: -0.1700

Data Index: 3208370 (Open Web Text)

Max Activating Token Index: 206

Text #1

Max Range: 5.6983. Min Range: -5.6983

Max Act: 5.6150. Min Act: -0.1700

Data Index: 8815690 (Open Web Text)

Max Activating Token Index: 537

Text #2

Max Range: 5.6983. Min Range: -5.6983

Max Act: 5.6176. Min Act: -0.1700

Data Index: 2514585 (Open Web Text)

Max Activating Token Index: 480

Text #3

Max Range: 5.6983. Min Range: -5.6983

Max Act: 5.6508. Min Act: -0.1700

Data Index: 5157236 (Open Web Text)

Max Activating Token Index: 458

Text #4

Max Range: 5.6983. Min Range: -5.6983

Max Act: 5.6341. Min Act: -0.1700

Data Index: 4957833 (Open Web Text)

Max Activating Token Index: 599

Text #5

Max Range: 5.6983. Min Range: -5.6983

Max Act: 5.5947. Min Act: -0.1700

Data Index: 2120211 (Open Web Text)

Max Activating Token Index: 672

Text #6

Max Range: 5.6983. Min Range: -5.6983

Max Act: 5.6068. Min Act: -0.1700

Data Index: 7922430 (Open Web Text)

Max Activating Token Index: 608

Text #7

Max Range: 5.6983. Min Range: -5.6983

Max Act: 5.5846. Min Act: -0.1700

Data Index: 8821860 (Open Web Text)

Max Activating Token Index: 362

Text #8

Max Range: 5.6983. Min Range: -5.6983

Max Act: 5.5523. Min Act: -0.1700

Data Index: 3835581 (Open Web Text)

Max Activating Token Index: 125

Text #9

Max Range: 5.6983. Min Range: -5.6983

Max Act: 5.5704. Min Act: -0.1700

Data Index: 7150952 (Open Web Text)

Max Activating Token Index: 987

Text #10

Max Range: 5.6983. Min Range: -5.6983

Max Act: 5.5466. Min Act: -0.1700

Data Index: 7157944 (Open Web Text)

Max Activating Token Index: 352

Text #11

Max Range: 5.6983. Min Range: -5.6983

Max Act: 5.5529. Min Act: -0.1700

Data Index: 4949873 (Open Web Text)

Max Activating Token Index: 207

Text #12

Max Range: 5.6983. Min Range: -5.6983

Max Act: 5.5770. Min Act: -0.1700

Data Index: 1053111 (Open Web Text)

Max Activating Token Index: 969

Text #13

Max Range: 5.6983. Min Range: -5.6983

Max Act: 5.5756. Min Act: -0.1700

Data Index: 7848588 (Open Web Text)

Max Activating Token Index: 809

Text #14

Max Range: 5.6983. Min Range: -5.6983

Max Act: 5.5707. Min Act: -0.1700

Data Index: 1797979 (Open Web Text)

Max Activating Token Index: 197

Text #15

Max Range: 5.6983. Min Range: -5.6983

Max Act: 5.5307. Min Act: -0.1700

Data Index: 4218303 (Open Web Text)

Max Activating Token Index: 70

Text #16

Max Range: 5.6983. Min Range: -5.6983

Max Act: 5.5587. Min Act: -0.1700

Data Index: 1831578 (Open Web Text)

Max Activating Token Index: 613

Text #17

Max Range: 5.6983. Min Range: -5.6983

Max Act: 5.5347. Min Act: -0.1700

Data Index: 7362406 (Open Web Text)

Max Activating Token Index: 34

Text #18

Max Range: 5.6983. Min Range: -5.6983

Max Act: 5.5134. Min Act: -0.1700

Data Index: 7362405 (Open Web Text)

Max Activating Token Index: 631

Text #19

Max Range: 5.6983. Min Range: -5.6983

Max Act: 5.5153. Min Act: -0.1700

Data Index: 1831585 (Open Web Text)

Max Activating Token Index: 379