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

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

Neuron 651 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: 0.9533. Min Range: -0.9533

Max Act: 0.9533. Min Act: 0.0000

Data Index: 1014264 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 0.9533. Min Range: -0.9533

Max Act: 0.9522. Min Act: 0.0000

Data Index: 971745 (C4 (Web Text))

Max Activating Token Index: 724

Text #2

Max Range: 0.9533. Min Range: -0.9533

Max Act: 0.8700. Min Act: 0.0000

Data Index: 950796 (C4 (Web Text))

Max Activating Token Index: 446

Text #3

Max Range: 0.9533. Min Range: -0.9533

Max Act: 0.8130. Min Act: 0.0000

Data Index: 64659 (C4 (Web Text))

Max Activating Token Index: 554

Text #4

Max Range: 0.9533. Min Range: -0.9533

Max Act: 0.7681. Min Act: 0.0000

Data Index: 545028 (C4 (Web Text))

Max Activating Token Index: 149

Text #5

Max Range: 0.9533. Min Range: -0.9533

Max Act: 0.7681. Min Act: -0.0000

Data Index: 146169 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 0.9533. Min Range: -0.9533

Max Act: 0.7886. Min Act: 0.0000

Data Index: 21744 (C4 (Web Text))

Max Activating Token Index: 407

Text #7

Max Range: 0.9533. Min Range: -0.9533

Max Act: 0.7650. Min Act: -0.0000

Data Index: 501493 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 0.9533. Min Range: -0.9533

Max Act: 0.7391. Min Act: -0.0000

Data Index: 597004 (C4 (Web Text))

Max Activating Token Index: 281

Text #9

Max Range: 0.9533. Min Range: -0.9533

Max Act: 0.7255. Min Act: -0.0000

Data Index: 950654 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 0.9533. Min Range: -0.9533

Max Act: 0.7164. Min Act: 0.0000

Data Index: 694494 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 0.9533. Min Range: -0.9533

Max Act: 0.6916. Min Act: -0.0000

Data Index: 602850 (C4 (Web Text))

Max Activating Token Index: 125

Text #12

Max Range: 0.9533. Min Range: -0.9533

Max Act: 0.6883. Min Act: 0.0000

Data Index: 63480 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 0.9533. Min Range: -0.9533

Max Act: 0.7042. Min Act: 0.0000

Data Index: 846845 (C4 (Web Text))

Max Activating Token Index: 947

Text #14

Max Range: 0.9533. Min Range: -0.9533

Max Act: 0.6469. Min Act: 0.0000

Data Index: 19847 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 0.9533. Min Range: -0.9533

Max Act: 0.6694. Min Act: 0.0000

Data Index: 559413 (C4 (Web Text))

Max Activating Token Index: 153

Text #16

Max Range: 0.9533. Min Range: -0.9533

Max Act: 0.6853. Min Act: 0.0000

Data Index: 1272418 (C4 (Web Text))

Max Activating Token Index: 438

Text #17

Max Range: 0.9533. Min Range: -0.9533

Max Act: 0.6537. Min Act: -0.0000

Data Index: 1229951 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 0.9533. Min Range: -0.9533

Max Act: 0.6317. Min Act: 0.0000

Data Index: 189124 (C4 (Web Text))

Max Activating Token Index: 437

Text #19

Max Range: 0.9533. Min Range: -0.9533

Max Act: 0.6542. Min Act: 0.0000

Data Index: 409430 (C4 (Web Text))

Max Activating Token Index: 518