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

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

Neuron 1450 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: 1.6921. Min Range: -1.6921

Max Act: 1.6095. Min Act: -0.0001

Data Index: 446203 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 1.6921. Min Range: -1.6921

Max Act: 1.5957. Min Act: -0.0001

Data Index: 202739 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 1.6921. Min Range: -1.6921

Max Act: 1.5803. Min Act: -0.0001

Data Index: 372130 (C4 (Web Text))

Max Activating Token Index: 262

Text #3

Max Range: 1.6921. Min Range: -1.6921

Max Act: 1.6009. Min Act: -0.0001

Data Index: 1118886 (C4 (Web Text))

Max Activating Token Index: 264

Text #4

Max Range: 1.6921. Min Range: -1.6921

Max Act: 1.5397. Min Act: -0.0001

Data Index: 644783 (C4 (Web Text))

Max Activating Token Index: 502

Text #5

Max Range: 1.6921. Min Range: -1.6921

Max Act: 1.6921. Min Act: -0.0001

Data Index: 791856 (C4 (Web Text))

Max Activating Token Index: 191

Text #6

Max Range: 1.6921. Min Range: -1.6921

Max Act: 1.4912. Min Act: -0.0001

Data Index: 1291807 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 1.6921. Min Range: -1.6921

Max Act: 1.6361. Min Act: -0.0001

Data Index: 351983 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 1.6921. Min Range: -1.6921

Max Act: 1.3863. Min Act: -0.0001

Data Index: 983658 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 1.6921. Min Range: -1.6921

Max Act: 1.3709. Min Act: -0.0001

Data Index: 621362 (C4 (Web Text))

Max Activating Token Index: 184

Text #10

Max Range: 1.6921. Min Range: -1.6921

Max Act: 1.4505. Min Act: -0.0001

Data Index: 443232 (C4 (Web Text))

Max Activating Token Index: 279

Text #11

Max Range: 1.6921. Min Range: -1.6921

Max Act: 1.4374. Min Act: -0.0001

Data Index: 938046 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 1.6921. Min Range: -1.6921

Max Act: 1.5031. Min Act: -0.0001

Data Index: 541622 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 1.6921. Min Range: -1.6921

Max Act: 1.4196. Min Act: -0.0001

Data Index: 782744 (C4 (Web Text))

Max Activating Token Index: 871

Text #14

Max Range: 1.6921. Min Range: -1.6921

Max Act: 1.4097. Min Act: -0.0001

Data Index: 1062323 (C4 (Web Text))

Max Activating Token Index: 671

Text #15

Max Range: 1.6921. Min Range: -1.6921

Max Act: 1.3102. Min Act: -0.0001

Data Index: 466235 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 1.6921. Min Range: -1.6921

Max Act: 1.4047. Min Act: -0.0001

Data Index: 356709 (C4 (Web Text))

Max Activating Token Index: 552

Text #17

Max Range: 1.6921. Min Range: -1.6921

Max Act: 1.4080. Min Act: -0.0001

Data Index: 833497 (C4 (Web Text))

Max Activating Token Index: 806

Text #18

Max Range: 1.6921. Min Range: -1.6921

Max Act: 1.3289. Min Act: -0.0001

Data Index: 176920 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 1.6921. Min Range: -1.6921

Max Act: 1.3163. Min Act: -0.0001

Data Index: 73942 (C4 (Web Text))

Max Activating Token Index: 762