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

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

Neuron 4119 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6458. Min Range: -1.6458

Max Act: 1.6458. Min Act: -0.0000

Data Index: 197168 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 1.6458. Min Range: -1.6458

Max Act: 1.4549. Min Act: -0.0000

Data Index: 38109 (C4 (Web Text))

Max Activating Token Index: 552

Text #2

Max Range: 1.6458. Min Range: -1.6458

Max Act: 1.3725. Min Act: -0.0000

Data Index: 934850 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 1.6458. Min Range: -1.6458

Max Act: 1.3300. Min Act: -0.0000

Data Index: 919211 (C4 (Web Text))

Max Activating Token Index: 341

Text #4

Max Range: 1.6458. Min Range: -1.6458

Max Act: 1.1917. Min Act: -0.0000

Data Index: 388485 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 1.6458. Min Range: -1.6458

Max Act: 1.1979. Min Act: -0.0000

Data Index: 298435 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 1.6458. Min Range: -1.6458

Max Act: 1.2400. Min Act: -0.0000

Data Index: 243479 (C4 (Web Text))

Max Activating Token Index: 746

Text #7

Max Range: 1.6458. Min Range: -1.6458

Max Act: 1.1814. Min Act: -0.0000

Data Index: 835199 (C4 (Web Text))

Max Activating Token Index: 943

Text #8

Max Range: 1.6458. Min Range: -1.6458

Max Act: 1.1566. Min Act: -0.0000

Data Index: 983472 (C4 (Web Text))

Max Activating Token Index: 685

Text #9

Max Range: 1.6458. Min Range: -1.6458

Max Act: 1.0981. Min Act: -0.0000

Data Index: 578097 (C4 (Web Text))

Max Activating Token Index: 235

Text #10

Max Range: 1.6458. Min Range: -1.6458

Max Act: 1.0973. Min Act: -0.0000

Data Index: 564151 (C4 (Web Text))

Max Activating Token Index: 293

Text #11

Max Range: 1.6458. Min Range: -1.6458

Max Act: 1.0306. Min Act: -0.0000

Data Index: 1047086 (C4 (Web Text))

Max Activating Token Index: 774

Text #12

Max Range: 1.6458. Min Range: -1.6458

Max Act: 1.0260. Min Act: -0.0000

Data Index: 1142548 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 1.6458. Min Range: -1.6458

Max Act: 0.9986. Min Act: -0.0000

Data Index: 826112 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 1.6458. Min Range: -1.6458

Max Act: 1.0154. Min Act: -0.0000

Data Index: 1021502 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 1.6458. Min Range: -1.6458

Max Act: 0.9809. Min Act: -0.0000

Data Index: 1233814 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 1.6458. Min Range: -1.6458

Max Act: 0.9705. Min Act: -0.0000

Data Index: 1047169 (C4 (Web Text))

Max Activating Token Index: 240

Text #17

Max Range: 1.6458. Min Range: -1.6458

Max Act: 1.0219. Min Act: -0.0000

Data Index: 703912 (C4 (Web Text))

Max Activating Token Index: 294

Text #18

Max Range: 1.6458. Min Range: -1.6458

Max Act: 0.9436. Min Act: -0.0000

Data Index: 476607 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 1.6458. Min Range: -1.6458

Max Act: 0.9717. Min Act: -0.0000

Data Index: 365447 (C4 (Web Text))

Max Activating Token Index: 523