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

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

Neuron 2857 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: 0.6943. Min Range: -0.6943

Max Act: 0.6943. Min Act: -0.0000

Data Index: 111853 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 0.6943. Min Range: -0.6943

Max Act: 0.5892. Min Act: -0.0000

Data Index: 170331 (C4 (Web Text))

Max Activating Token Index: 964

Text #2

Max Range: 0.6943. Min Range: -0.6943

Max Act: 0.5481. Min Act: -0.0000

Data Index: 597485 (C4 (Web Text))

Max Activating Token Index: 700

Text #3

Max Range: 0.6943. Min Range: -0.6943

Max Act: 0.5276. Min Act: -0.0000

Data Index: 385918 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 0.6943. Min Range: -0.6943

Max Act: 0.5155. Min Act: -0.0000

Data Index: 1325075 (C4 (Web Text))

Max Activating Token Index: 524

Text #5

Max Range: 0.6943. Min Range: -0.6943

Max Act: 0.5382. Min Act: -0.0000

Data Index: 1222051 (C4 (Web Text))

Max Activating Token Index: 923

Text #6

Max Range: 0.6943. Min Range: -0.6943

Max Act: 0.5106. Min Act: -0.0000

Data Index: 1136269 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 0.6943. Min Range: -0.6943

Max Act: 0.5244. Min Act: -0.0000

Data Index: 496377 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 0.6943. Min Range: -0.6943

Max Act: 0.4655. Min Act: -0.0000

Data Index: 774694 (C4 (Web Text))

Max Activating Token Index: 850

Text #9

Max Range: 0.6943. Min Range: -0.6943

Max Act: 0.4902. Min Act: -0.0000

Data Index: 1271966 (C4 (Web Text))

Max Activating Token Index: 95

Text #10

Max Range: 0.6943. Min Range: -0.6943

Max Act: 0.4390. Min Act: -0.0000

Data Index: 806503 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 0.6943. Min Range: -0.6943

Max Act: 0.4690. Min Act: -0.0000

Data Index: 68456 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 0.6943. Min Range: -0.6943

Max Act: 0.4063. Min Act: -0.0000

Data Index: 986540 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 0.6943. Min Range: -0.6943

Max Act: 0.4169. Min Act: -0.0000

Data Index: 464391 (C4 (Web Text))

Max Activating Token Index: 359

Text #14

Max Range: 0.6943. Min Range: -0.6943

Max Act: 0.4731. Min Act: -0.0000

Data Index: 725313 (C4 (Web Text))

Max Activating Token Index: 974

Text #15

Max Range: 0.6943. Min Range: -0.6943

Max Act: 0.4399. Min Act: -0.0000

Data Index: 112479 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 0.6943. Min Range: -0.6943

Max Act: 0.4408. Min Act: -0.0000

Data Index: 670877 (C4 (Web Text))

Max Activating Token Index: 706

Text #17

Max Range: 0.6943. Min Range: -0.6943

Max Act: 0.4625. Min Act: -0.0000

Data Index: 477209 (C4 (Web Text))

Max Activating Token Index: 924

Text #18

Max Range: 0.6943. Min Range: -0.6943

Max Act: 0.4478. Min Act: -0.0000

Data Index: 966744 (C4 (Web Text))

Max Activating Token Index: 625

Text #19

Max Range: 0.6943. Min Range: -0.6943

Max Act: 0.4305. Min Act: -0.0000

Data Index: 859749 (C4 (Web Text))

Max Activating Token Index: 576