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

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

Neuron 5800 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: 1.0948. Min Range: -1.0948

Max Act: 1.0948. Min Act: -0.0000

Data Index: 641864 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.8240. Min Act: -0.0000

Data Index: 1101121 (C4 (Web Text))

Max Activating Token Index: 993

Text #2

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.8507. Min Act: -0.0000

Data Index: 1210625 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.8597. Min Act: -0.0000

Data Index: 1180631 (C4 (Web Text))

Max Activating Token Index: 396

Text #4

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.8020. Min Act: -0.0000

Data Index: 1150283 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.8235. Min Act: -0.0000

Data Index: 692968 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.8060. Min Act: -0.0000

Data Index: 526414 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.7622. Min Act: -0.0000

Data Index: 713795 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.8170. Min Act: -0.0000

Data Index: 1220147 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.7308. Min Act: -0.0000

Data Index: 775372 (C4 (Web Text))

Max Activating Token Index: 878

Text #10

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.7775. Min Act: -0.0000

Data Index: 43725 (C4 (Web Text))

Max Activating Token Index: 262

Text #11

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.7833. Min Act: -0.0000

Data Index: 707583 (C4 (Web Text))

Max Activating Token Index: 261

Text #12

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.7971. Min Act: -0.0000

Data Index: 89858 (C4 (Web Text))

Max Activating Token Index: 173

Text #13

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.7450. Min Act: -0.0000

Data Index: 441570 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.7415. Min Act: -0.0000

Data Index: 376208 (C4 (Web Text))

Max Activating Token Index: 651

Text #15

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.6980. Min Act: -0.0000

Data Index: 866972 (C4 (Web Text))

Max Activating Token Index: 224

Text #16

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.7131. Min Act: -0.0000

Data Index: 974146 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.7562. Min Act: -0.0000

Data Index: 1068612 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.7860. Min Act: -0.0000

Data Index: 513555 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 1.0948. Min Range: -1.0948

Max Act: 0.7518. Min Act: -0.0000

Data Index: 1041636 (C4 (Web Text))

Max Activating Token Index: 219