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

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

Neuron 1690 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.2440. Min Act: -0.0000

Data Index: 207592 (C4 (Web Text))

Max Activating Token Index: 643

Text #1

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.2371. Min Act: -0.0000

Data Index: 1103371 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.2310. Min Act: -0.0000

Data Index: 1235856 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.2272. Min Act: -0.0000

Data Index: 366256 (C4 (Web Text))

Max Activating Token Index: 255

Text #4

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.2298. Min Act: -0.0001

Data Index: 1308608 (C4 (Web Text))

Max Activating Token Index: 619

Text #5

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.2253. Min Act: -0.0000

Data Index: 512947 (C4 (Web Text))

Max Activating Token Index: 764

Text #6

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.2237. Min Act: -0.0001

Data Index: 518959 (C4 (Web Text))

Max Activating Token Index: 439

Text #7

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.2427. Min Act: -0.0000

Data Index: 699687 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.2140. Min Act: -0.0001

Data Index: 503805 (C4 (Web Text))

Max Activating Token Index: 61

Text #9

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.2131. Min Act: -0.0001

Data Index: 786880 (C4 (Web Text))

Max Activating Token Index: 568

Text #10

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.2064. Min Act: -0.0001

Data Index: 800242 (C4 (Web Text))

Max Activating Token Index: 607

Text #11

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.2108. Min Act: -0.0001

Data Index: 1156051 (C4 (Web Text))

Max Activating Token Index: 843

Text #12

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.2004. Min Act: -0.0000

Data Index: 862533 (C4 (Web Text))

Max Activating Token Index: 342

Text #13

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.2033. Min Act: -0.0000

Data Index: 289970 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.2017. Min Act: -0.0000

Data Index: 167220 (C4 (Web Text))

Max Activating Token Index: 969

Text #15

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.2061. Min Act: -0.0000

Data Index: 840212 (C4 (Web Text))

Max Activating Token Index: 888

Text #16

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.2051. Min Act: -0.0000

Data Index: 1242952 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.1893. Min Act: -0.0000

Data Index: 60288 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.1970. Min Act: -0.0000

Data Index: 1020449 (C4 (Web Text))

Max Activating Token Index: 742

Text #19

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.1935. Min Act: -0.0000

Data Index: 727224 (C4 (Web Text))

Max Activating Token Index: 382