Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1073 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1964. Min Act: -0.0000

Data Index: 1007043 (C4 (Web Text))

Max Activating Token Index: 276

Text #1

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1777. Min Act: -0.0000

Data Index: 924703 (C4 (Web Text))

Max Activating Token Index: 623

Text #2

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1552. Min Act: -0.0000

Data Index: 629256 (C4 (Web Text))

Max Activating Token Index: 975

Text #3

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1629. Min Act: -0.0000

Data Index: 54659 (C4 (Web Text))

Max Activating Token Index: 529

Text #4

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1471. Min Act: -0.0000

Data Index: 300394 (C4 (Web Text))

Max Activating Token Index: 217

Text #5

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1401. Min Act: -0.0000

Data Index: 136739 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1417. Min Act: -0.0000

Data Index: 1090485 (C4 (Web Text))

Max Activating Token Index: 599

Text #7

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1357. Min Act: -0.0000

Data Index: 759634 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1331. Min Act: -0.0000

Data Index: 789506 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1327. Min Act: -0.0000

Data Index: 972813 (C4 (Web Text))

Max Activating Token Index: 458

Text #10

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1298. Min Act: -0.0000

Data Index: 695923 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1136. Min Act: -0.0000

Data Index: 533022 (C4 (Web Text))

Max Activating Token Index: 874

Text #12

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1298. Min Act: -0.0000

Data Index: 1140457 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1241. Min Act: -0.0000

Data Index: 655859 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1315. Min Act: -0.0000

Data Index: 182595 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1267. Min Act: -0.0000

Data Index: 1251609 (C4 (Web Text))

Max Activating Token Index: 994

Text #16

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1188. Min Act: -0.0000

Data Index: 1017236 (C4 (Web Text))

Max Activating Token Index: 985

Text #17

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1285. Min Act: -0.0000

Data Index: 295885 (C4 (Web Text))

Max Activating Token Index: 334

Text #18

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1275. Min Act: -0.0000

Data Index: 483580 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1242. Min Act: -0.0000

Data Index: 1337474 (C4 (Web Text))

Max Activating Token Index: 136