Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1541 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.7749. Min Act: -0.0002

Data Index: 762176 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.7731. Min Act: -0.0002

Data Index: 350953 (C4 (Web Text))

Max Activating Token Index: 643

Text #2

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.7187. Min Act: -0.0002

Data Index: 725828 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.6183. Min Act: -0.0003

Data Index: 923004 (C4 (Web Text))

Max Activating Token Index: 1000

Text #4

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.6374. Min Act: -0.0002

Data Index: 1062675 (C4 (Web Text))

Max Activating Token Index: 783

Text #5

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.5943. Min Act: -0.0003

Data Index: 116588 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.6251. Min Act: -0.0003

Data Index: 918963 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.5989. Min Act: -0.0002

Data Index: 732328 (C4 (Web Text))

Max Activating Token Index: 762

Text #8

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.5839. Min Act: -0.0003

Data Index: 1101383 (C4 (Web Text))

Max Activating Token Index: 788

Text #9

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.5941. Min Act: -0.0003

Data Index: 231006 (C4 (Web Text))

Max Activating Token Index: 126

Text #10

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.5937. Min Act: -0.0003

Data Index: 1013082 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.5809. Min Act: -0.0003

Data Index: 1241321 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.5961. Min Act: -0.0003

Data Index: 356268 (C4 (Web Text))

Max Activating Token Index: 553

Text #13

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.5939. Min Act: -0.0002

Data Index: 325912 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.5385. Min Act: -0.0003

Data Index: 306001 (C4 (Web Text))

Max Activating Token Index: 1008

Text #15

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.5747. Min Act: -0.0002

Data Index: 275320 (C4 (Web Text))

Max Activating Token Index: 952

Text #16

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.6078. Min Act: -0.0003

Data Index: 1004327 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.5863. Min Act: -0.0002

Data Index: 2994 (C4 (Web Text))

Max Activating Token Index: 348

Text #18

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.5965. Min Act: -0.0002

Data Index: 1074399 (C4 (Web Text))

Max Activating Token Index: 257

Text #19

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.5636. Min Act: -0.0003

Data Index: 409006 (C4 (Web Text))

Max Activating Token Index: 272