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

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

Neuron 1507 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8206. Min Range: -5.8206

Max Act: 5.6449. Min Act: -0.0000

Data Index: 141169 (C4 (Web Text))

Max Activating Token Index: 245

Text #1

Max Range: 5.8206. Min Range: -5.8206

Max Act: 5.8206. Min Act: -0.0000

Data Index: 903256 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 5.8206. Min Range: -5.8206

Max Act: 4.7279. Min Act: -0.0000

Data Index: 489650 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 5.8206. Min Range: -5.8206

Max Act: 4.1590. Min Act: -0.0000

Data Index: 478694 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 5.8206. Min Range: -5.8206

Max Act: 4.4842. Min Act: -0.0000

Data Index: 871062 (C4 (Web Text))

Max Activating Token Index: 871

Text #5

Max Range: 5.8206. Min Range: -5.8206

Max Act: 4.1310. Min Act: -0.0000

Data Index: 437439 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 5.8206. Min Range: -5.8206

Max Act: 4.0774. Min Act: -0.0000

Data Index: 614696 (C4 (Web Text))

Max Activating Token Index: 687

Text #7

Max Range: 5.8206. Min Range: -5.8206

Max Act: 4.0039. Min Act: -0.0000

Data Index: 1321757 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 5.8206. Min Range: -5.8206

Max Act: 3.1415. Min Act: -0.0000

Data Index: 173784 (C4 (Web Text))

Max Activating Token Index: 947

Text #9

Max Range: 5.8206. Min Range: -5.8206

Max Act: 2.8439. Min Act: -0.0000

Data Index: 24469 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 5.8206. Min Range: -5.8206

Max Act: 2.6110. Min Act: -0.0000

Data Index: 1188245 (C4 (Web Text))

Max Activating Token Index: 545

Text #11

Max Range: 5.8206. Min Range: -5.8206

Max Act: 2.4481. Min Act: -0.0000

Data Index: 779941 (C4 (Web Text))

Max Activating Token Index: 238

Text #12

Max Range: 5.8206. Min Range: -5.8206

Max Act: 2.2357. Min Act: -0.0000

Data Index: 1105025 (C4 (Web Text))

Max Activating Token Index: 198

Text #13

Max Range: 5.8206. Min Range: -5.8206

Max Act: 2.2513. Min Act: -0.0000

Data Index: 677238 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 5.8206. Min Range: -5.8206

Max Act: 2.2123. Min Act: -0.0000

Data Index: 227396 (C4 (Web Text))

Max Activating Token Index: 720

Text #15

Max Range: 5.8206. Min Range: -5.8206

Max Act: 2.1499. Min Act: -0.0000

Data Index: 364467 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 5.8206. Min Range: -5.8206

Max Act: 2.0124. Min Act: -0.0000

Data Index: 579886 (C4 (Web Text))

Max Activating Token Index: 998

Text #17

Max Range: 5.8206. Min Range: -5.8206

Max Act: 2.0672. Min Act: -0.0000

Data Index: 96851 (C4 (Web Text))

Max Activating Token Index: 584

Text #18

Max Range: 5.8206. Min Range: -5.8206

Max Act: 1.9364. Min Act: -0.0000

Data Index: 1250887 (C4 (Web Text))

Max Activating Token Index: 984

Text #19

Max Range: 5.8206. Min Range: -5.8206

Max Act: 2.0568. Min Act: -0.0000

Data Index: 180542 (C4 (Web Text))

Max Activating Token Index: 783