Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1315 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2943. Min Act: -0.0001

Data Index: 1493985 (Python Code)

Max Activating Token Index: 727

Text #1

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2874. Min Act: -0.0000

Data Index: 1353366 (C4 (Web Text))

Max Activating Token Index: 411

Text #2

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2532. Min Act: -0.0001

Data Index: 1404282 (Python Code)

Max Activating Token Index: 578

Text #3

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2533. Min Act: -0.0001

Data Index: 1334500 (C4 (Web Text))

Max Activating Token Index: 125

Text #4

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2491. Min Act: -0.0000

Data Index: 1015756 (C4 (Web Text))

Max Activating Token Index: 265

Text #5

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2431. Min Act: -0.0000

Data Index: 627576 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2414. Min Act: -0.0000

Data Index: 171601 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2455. Min Act: -0.0001

Data Index: 1581777 (Python Code)

Max Activating Token Index: 151

Text #8

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2045. Min Act: -0.0000

Data Index: 943545 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2387. Min Act: -0.0000

Data Index: 1230475 (C4 (Web Text))

Max Activating Token Index: 900

Text #10

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2296. Min Act: -0.0000

Data Index: 397779 (C4 (Web Text))

Max Activating Token Index: 300

Text #11

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2238. Min Act: -0.0001

Data Index: 1630866 (Python Code)

Max Activating Token Index: 273

Text #12

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.1980. Min Act: -0.0001

Data Index: 1441680 (Python Code)

Max Activating Token Index: 983

Text #13

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2349. Min Act: -0.0000

Data Index: 550182 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2144. Min Act: -0.0001

Data Index: 1457130 (Python Code)

Max Activating Token Index: 155

Text #15

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2033. Min Act: -0.0001

Data Index: 1404404 (Python Code)

Max Activating Token Index: 243

Text #16

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.1993. Min Act: -0.0000

Data Index: 111018 (C4 (Web Text))

Max Activating Token Index: 923

Text #17

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2001. Min Act: -0.0001

Data Index: 796379 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2056. Min Act: -0.0000

Data Index: 375392 (C4 (Web Text))

Max Activating Token Index: 770

Text #19

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2015. Min Act: -0.0000

Data Index: 1274907 (C4 (Web Text))

Max Activating Token Index: 797