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

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

Neuron 45 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: 0.9105. Min Range: -0.9105

Max Act: 0.9105. Min Act: -0.0000

Data Index: 62177 (C4 (Web Text))

Max Activating Token Index: 370

Text #1

Max Range: 0.9105. Min Range: -0.9105

Max Act: 0.8978. Min Act: -0.0000

Data Index: 1014505 (C4 (Web Text))

Max Activating Token Index: 938

Text #2

Max Range: 0.9105. Min Range: -0.9105

Max Act: 0.8325. Min Act: -0.0000

Data Index: 315637 (C4 (Web Text))

Max Activating Token Index: 635

Text #3

Max Range: 0.9105. Min Range: -0.9105

Max Act: 0.8750. Min Act: -0.0000

Data Index: 184993 (C4 (Web Text))

Max Activating Token Index: 966

Text #4

Max Range: 0.9105. Min Range: -0.9105

Max Act: 0.8264. Min Act: -0.0000

Data Index: 283485 (C4 (Web Text))

Max Activating Token Index: 655

Text #5

Max Range: 0.9105. Min Range: -0.9105

Max Act: 0.8467. Min Act: -0.0000

Data Index: 1159157 (C4 (Web Text))

Max Activating Token Index: 766

Text #6

Max Range: 0.9105. Min Range: -0.9105

Max Act: 0.7956. Min Act: -0.0000

Data Index: 812289 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 0.9105. Min Range: -0.9105

Max Act: 0.8183. Min Act: -0.0000

Data Index: 141555 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 0.9105. Min Range: -0.9105

Max Act: 0.8000. Min Act: -0.0000

Data Index: 655085 (C4 (Web Text))

Max Activating Token Index: 591

Text #9

Max Range: 0.9105. Min Range: -0.9105

Max Act: 0.7979. Min Act: -0.0000

Data Index: 1067406 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 0.9105. Min Range: -0.9105

Max Act: 0.8140. Min Act: -0.0000

Data Index: 687020 (C4 (Web Text))

Max Activating Token Index: 606

Text #11

Max Range: 0.9105. Min Range: -0.9105

Max Act: 0.7820. Min Act: -0.0000

Data Index: 787514 (C4 (Web Text))

Max Activating Token Index: 604

Text #12

Max Range: 0.9105. Min Range: -0.9105

Max Act: 0.7545. Min Act: -0.0000

Data Index: 213521 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 0.9105. Min Range: -0.9105

Max Act: 0.7821. Min Act: -0.0000

Data Index: 532989 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 0.9105. Min Range: -0.9105

Max Act: 0.7486. Min Act: -0.0000

Data Index: 483380 (C4 (Web Text))

Max Activating Token Index: 580

Text #15

Max Range: 0.9105. Min Range: -0.9105

Max Act: 0.7724. Min Act: -0.0000

Data Index: 325533 (C4 (Web Text))

Max Activating Token Index: 332

Text #16

Max Range: 0.9105. Min Range: -0.9105

Max Act: 0.7677. Min Act: -0.0000

Data Index: 1258666 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 0.9105. Min Range: -0.9105

Max Act: 0.7456. Min Act: -0.0000

Data Index: 1087984 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 0.9105. Min Range: -0.9105

Max Act: 0.7410. Min Act: -0.0000

Data Index: 695069 (C4 (Web Text))

Max Activating Token Index: 528

Text #19

Max Range: 0.9105. Min Range: -0.9105

Max Act: 0.7865. Min Act: -0.0000

Data Index: 521588 (C4 (Web Text))

Max Activating Token Index: 532