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

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

Neuron 74 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.3007. Min Act: -0.0001

Data Index: 890639 (C4 (Web Text))

Max Activating Token Index: 1016

Text #1

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2414. Min Act: -0.0001

Data Index: 310682 (C4 (Web Text))

Max Activating Token Index: 782

Text #2

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2435. Min Act: -0.0001

Data Index: 454671 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2692. Min Act: -0.0001

Data Index: 1278652 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2261. Min Act: -0.0001

Data Index: 108252 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2069. Min Act: -0.0001

Data Index: 998203 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2264. Min Act: -0.0001

Data Index: 345779 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2210. Min Act: -0.0001

Data Index: 1083771 (C4 (Web Text))

Max Activating Token Index: 433

Text #8

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2113. Min Act: -0.0001

Data Index: 119811 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2027. Min Act: -0.0001

Data Index: 3799 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2193. Min Act: -0.0001

Data Index: 335573 (C4 (Web Text))

Max Activating Token Index: 510

Text #11

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2164. Min Act: -0.0000

Data Index: 494510 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2400. Min Act: -0.0001

Data Index: 1003292 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2074. Min Act: -0.0001

Data Index: 4395 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.1943. Min Act: -0.0001

Data Index: 3677 (C4 (Web Text))

Max Activating Token Index: 669

Text #15

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.1928. Min Act: -0.0001

Data Index: 348143 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2131. Min Act: -0.0001

Data Index: 1271805 (C4 (Web Text))

Max Activating Token Index: 632

Text #17

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2269. Min Act: -0.0001

Data Index: 1116087 (C4 (Web Text))

Max Activating Token Index: 946

Text #18

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2005. Min Act: -0.0001

Data Index: 1335579 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2081. Min Act: -0.0001

Data Index: 685437 (C4 (Web Text))

Max Activating Token Index: 480