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

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

Neuron 4074 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.4088. Min Range: -2.4088

Max Act: 2.3979. Min Act: -0.0000

Data Index: 509844 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 2.4088. Min Range: -2.4088

Max Act: 2.4088. Min Act: -0.0000

Data Index: 9676 (C4 (Web Text))

Max Activating Token Index: 524

Text #2

Max Range: 2.4088. Min Range: -2.4088

Max Act: 2.0100. Min Act: -0.0000

Data Index: 1179383 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 2.4088. Min Range: -2.4088

Max Act: 2.0252. Min Act: -0.0000

Data Index: 1353408 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 2.4088. Min Range: -2.4088

Max Act: 2.0220. Min Act: -0.0000

Data Index: 874008 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 2.4088. Min Range: -2.4088

Max Act: 1.9958. Min Act: -0.0000

Data Index: 123991 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 2.4088. Min Range: -2.4088

Max Act: 1.9167. Min Act: -0.0000

Data Index: 1076246 (C4 (Web Text))

Max Activating Token Index: 659

Text #7

Max Range: 2.4088. Min Range: -2.4088

Max Act: 1.9115. Min Act: -0.0000

Data Index: 728065 (C4 (Web Text))

Max Activating Token Index: 1015

Text #8

Max Range: 2.4088. Min Range: -2.4088

Max Act: 1.8850. Min Act: -0.0000

Data Index: 49883 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 2.4088. Min Range: -2.4088

Max Act: 1.8623. Min Act: -0.0000

Data Index: 317921 (C4 (Web Text))

Max Activating Token Index: 614

Text #10

Max Range: 2.4088. Min Range: -2.4088

Max Act: 1.8516. Min Act: -0.0000

Data Index: 311615 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 2.4088. Min Range: -2.4088

Max Act: 1.8114. Min Act: -0.0000

Data Index: 1256430 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 2.4088. Min Range: -2.4088

Max Act: 1.6677. Min Act: -0.0000

Data Index: 553547 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 2.4088. Min Range: -2.4088

Max Act: 1.5269. Min Act: -0.0000

Data Index: 976562 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 2.4088. Min Range: -2.4088

Max Act: 1.6752. Min Act: -0.0000

Data Index: 881497 (C4 (Web Text))

Max Activating Token Index: 433

Text #15

Max Range: 2.4088. Min Range: -2.4088

Max Act: 1.5618. Min Act: -0.0000

Data Index: 200042 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 2.4088. Min Range: -2.4088

Max Act: 1.5348. Min Act: -0.0000

Data Index: 1341752 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 2.4088. Min Range: -2.4088

Max Act: 1.4938. Min Act: -0.0000

Data Index: 753145 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 2.4088. Min Range: -2.4088

Max Act: 1.4945. Min Act: -0.0000

Data Index: 985336 (C4 (Web Text))

Max Activating Token Index: 962

Text #19

Max Range: 2.4088. Min Range: -2.4088

Max Act: 1.3952. Min Act: -0.0000

Data Index: 18869 (C4 (Web Text))

Max Activating Token Index: 340