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

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

Neuron 631 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: 0.2409. Min Act: -0.0001

Data Index: 213199 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.2440. Min Act: -0.0000

Data Index: 140162 (C4 (Web Text))

Max Activating Token Index: 483

Text #2

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.2294. Min Act: -0.0001

Data Index: 568618 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.2231. Min Act: -0.0001

Data Index: 322630 (C4 (Web Text))

Max Activating Token Index: 754

Text #4

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.2270. Min Act: -0.0001

Data Index: 801518 (C4 (Web Text))

Max Activating Token Index: 759

Text #5

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.2148. Min Act: -0.0001

Data Index: 1070844 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.2186. Min Act: -0.0001

Data Index: 1256342 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.2103. Min Act: -0.0001

Data Index: 347806 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.2178. Min Act: -0.0000

Data Index: 86787 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.2145. Min Act: -0.0001

Data Index: 29279 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.1918. Min Act: -0.0000

Data Index: 483537 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.1953. Min Act: -0.0001

Data Index: 631452 (C4 (Web Text))

Max Activating Token Index: 674

Text #12

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.1932. Min Act: -0.0001

Data Index: 666127 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.1913. Min Act: -0.0000

Data Index: 305997 (C4 (Web Text))

Max Activating Token Index: 983

Text #14

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.1908. Min Act: -0.0000

Data Index: 1267328 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.1961. Min Act: 0.0001

Data Index: 9329 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.1828. Min Act: -0.0000

Data Index: 370874 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.1835. Min Act: -0.0001

Data Index: 236225 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.1866. Min Act: -0.0001

Data Index: 1289949 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 0.2440. Min Range: -0.2440

Max Act: 0.1842. Min Act: -0.0001

Data Index: 289106 (C4 (Web Text))

Max Activating Token Index: 448