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

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

Neuron 3907 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2922. Min Act: -0.0000

Data Index: 628868 (C4 (Web Text))

Max Activating Token Index: 167

Text #1

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2663. Min Act: -0.0000

Data Index: 963494 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2532. Min Act: -0.0000

Data Index: 591126 (C4 (Web Text))

Max Activating Token Index: 787

Text #3

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2693. Min Act: -0.0000

Data Index: 268466 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2483. Min Act: -0.0000

Data Index: 1096495 (C4 (Web Text))

Max Activating Token Index: 194

Text #5

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2449. Min Act: -0.0000

Data Index: 1010741 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2497. Min Act: -0.0001

Data Index: 534289 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2396. Min Act: -0.0001

Data Index: 231642 (C4 (Web Text))

Max Activating Token Index: 761

Text #8

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2439. Min Act: -0.0001

Data Index: 1175642 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2186. Min Act: -0.0000

Data Index: 1352493 (C4 (Web Text))

Max Activating Token Index: 783

Text #10

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2374. Min Act: -0.0000

Data Index: 166740 (C4 (Web Text))

Max Activating Token Index: 876

Text #11

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2149. Min Act: -0.0000

Data Index: 980970 (C4 (Web Text))

Max Activating Token Index: 83

Text #12

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2256. Min Act: -0.0000

Data Index: 707261 (C4 (Web Text))

Max Activating Token Index: 110

Text #13

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2278. Min Act: -0.0001

Data Index: 242176 (C4 (Web Text))

Max Activating Token Index: 830

Text #14

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2050. Min Act: -0.0001

Data Index: 545607 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2407. Min Act: -0.0000

Data Index: 476462 (C4 (Web Text))

Max Activating Token Index: 303

Text #16

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2157. Min Act: -0.0000

Data Index: 717350 (C4 (Web Text))

Max Activating Token Index: 785

Text #17

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2237. Min Act: -0.0000

Data Index: 1067821 (C4 (Web Text))

Max Activating Token Index: 1004

Text #18

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2298. Min Act: -0.0000

Data Index: 1066164 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2177. Min Act: -0.0000

Data Index: 57885 (C4 (Web Text))

Max Activating Token Index: 361