Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 767 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0164. Min Range: -2.0164

Max Act: 2.0164. Min Act: -0.0000

Data Index: 258131 (C4 (Web Text))

Max Activating Token Index: 818

Text #1

Max Range: 2.0164. Min Range: -2.0164

Max Act: 1.9448. Min Act: -0.0000

Data Index: 945819 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 2.0164. Min Range: -2.0164

Max Act: 1.8961. Min Act: -0.0000

Data Index: 302823 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 2.0164. Min Range: -2.0164

Max Act: 1.8392. Min Act: -0.0000

Data Index: 428888 (C4 (Web Text))

Max Activating Token Index: 335

Text #4

Max Range: 2.0164. Min Range: -2.0164

Max Act: 1.9431. Min Act: -0.0000

Data Index: 902271 (C4 (Web Text))

Max Activating Token Index: 502

Text #5

Max Range: 2.0164. Min Range: -2.0164

Max Act: 1.8267. Min Act: -0.0000

Data Index: 306746 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 2.0164. Min Range: -2.0164

Max Act: 1.8287. Min Act: -0.0000

Data Index: 970455 (C4 (Web Text))

Max Activating Token Index: 528

Text #7

Max Range: 2.0164. Min Range: -2.0164

Max Act: 1.7888. Min Act: -0.0000

Data Index: 803502 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 2.0164. Min Range: -2.0164

Max Act: 1.7777. Min Act: -0.0000

Data Index: 79209 (C4 (Web Text))

Max Activating Token Index: 537

Text #9

Max Range: 2.0164. Min Range: -2.0164

Max Act: 1.7658. Min Act: -0.0000

Data Index: 394598 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 2.0164. Min Range: -2.0164

Max Act: 1.7365. Min Act: -0.0000

Data Index: 1032183 (C4 (Web Text))

Max Activating Token Index: 536

Text #11

Max Range: 2.0164. Min Range: -2.0164

Max Act: 1.7395. Min Act: -0.0000

Data Index: 840704 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 2.0164. Min Range: -2.0164

Max Act: 1.7347. Min Act: -0.0000

Data Index: 1319246 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 2.0164. Min Range: -2.0164

Max Act: 1.7196. Min Act: -0.0000

Data Index: 105916 (C4 (Web Text))

Max Activating Token Index: 512

Text #14

Max Range: 2.0164. Min Range: -2.0164

Max Act: 1.6371. Min Act: -0.0000

Data Index: 256585 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 2.0164. Min Range: -2.0164

Max Act: 1.7141. Min Act: -0.0000

Data Index: 1105441 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 2.0164. Min Range: -2.0164

Max Act: 1.6958. Min Act: -0.0000

Data Index: 1077575 (C4 (Web Text))

Max Activating Token Index: 297

Text #17

Max Range: 2.0164. Min Range: -2.0164

Max Act: 1.6672. Min Act: -0.0000

Data Index: 483321 (C4 (Web Text))

Max Activating Token Index: 872

Text #18

Max Range: 2.0164. Min Range: -2.0164

Max Act: 1.6394. Min Act: -0.0000

Data Index: 475494 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 2.0164. Min Range: -2.0164

Max Act: 1.7186. Min Act: 0.0000

Data Index: 1318940 (C4 (Web Text))

Max Activating Token Index: 560