Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2127 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8645. Min Range: -1.8645

Max Act: 1.8645. Min Act: -0.0001

Data Index: 965947 (C4 (Web Text))

Max Activating Token Index: 512

Text #1

Max Range: 1.8645. Min Range: -1.8645

Max Act: 1.8262. Min Act: -0.0001

Data Index: 1320772 (C4 (Web Text))

Max Activating Token Index: 671

Text #2

Max Range: 1.8645. Min Range: -1.8645

Max Act: 1.6118. Min Act: -0.0001

Data Index: 234840 (C4 (Web Text))

Max Activating Token Index: 707

Text #3

Max Range: 1.8645. Min Range: -1.8645

Max Act: 1.4671. Min Act: -0.0001

Data Index: 96327 (C4 (Web Text))

Max Activating Token Index: 332

Text #4

Max Range: 1.8645. Min Range: -1.8645

Max Act: 1.5014. Min Act: -0.0001

Data Index: 531734 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 1.8645. Min Range: -1.8645

Max Act: 1.4174. Min Act: -0.0001

Data Index: 207776 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 1.8645. Min Range: -1.8645

Max Act: 1.3412. Min Act: -0.0001

Data Index: 881552 (C4 (Web Text))

Max Activating Token Index: 713

Text #7

Max Range: 1.8645. Min Range: -1.8645

Max Act: 1.5466. Min Act: -0.0001

Data Index: 762947 (C4 (Web Text))

Max Activating Token Index: 207

Text #8

Max Range: 1.8645. Min Range: -1.8645

Max Act: 1.4244. Min Act: -0.0001

Data Index: 1246269 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 1.8645. Min Range: -1.8645

Max Act: 1.4138. Min Act: -0.0001

Data Index: 469191 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 1.8645. Min Range: -1.8645

Max Act: 1.4092. Min Act: -0.0001

Data Index: 914770 (C4 (Web Text))

Max Activating Token Index: 110

Text #11

Max Range: 1.8645. Min Range: -1.8645

Max Act: 1.3054. Min Act: -0.0001

Data Index: 1453488 (Python Code)

Max Activating Token Index: 755

Text #12

Max Range: 1.8645. Min Range: -1.8645

Max Act: 1.3064. Min Act: -0.0001

Data Index: 291162 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 1.8645. Min Range: -1.8645

Max Act: 1.2346. Min Act: -0.0001

Data Index: 536800 (C4 (Web Text))

Max Activating Token Index: 830

Text #14

Max Range: 1.8645. Min Range: -1.8645

Max Act: 1.2505. Min Act: -0.0001

Data Index: 1141339 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 1.8645. Min Range: -1.8645

Max Act: 1.3235. Min Act: -0.0001

Data Index: 1044054 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 1.8645. Min Range: -1.8645

Max Act: 1.2514. Min Act: -0.0001

Data Index: 1235244 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 1.8645. Min Range: -1.8645

Max Act: 1.1656. Min Act: -0.0001

Data Index: 746188 (C4 (Web Text))

Max Activating Token Index: 958

Text #18

Max Range: 1.8645. Min Range: -1.8645

Max Act: 1.2286. Min Act: -0.0001

Data Index: 464497 (C4 (Web Text))

Max Activating Token Index: 997

Text #19

Max Range: 1.8645. Min Range: -1.8645

Max Act: 1.0481. Min Act: -0.0001

Data Index: 478373 (C4 (Web Text))

Max Activating Token Index: 334