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

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

Neuron 1192 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6321. Min Range: -0.6321

Max Act: 0.6321. Min Act: -0.0000

Data Index: 247514 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 0.6321. Min Range: -0.6321

Max Act: 0.5650. Min Act: -0.0000

Data Index: 147111 (C4 (Web Text))

Max Activating Token Index: 488

Text #2

Max Range: 0.6321. Min Range: -0.6321

Max Act: 0.4473. Min Act: -0.0000

Data Index: 212975 (C4 (Web Text))

Max Activating Token Index: 938

Text #3

Max Range: 0.6321. Min Range: -0.6321

Max Act: 0.4312. Min Act: -0.0000

Data Index: 1293676 (C4 (Web Text))

Max Activating Token Index: 209

Text #4

Max Range: 0.6321. Min Range: -0.6321

Max Act: 0.4269. Min Act: -0.0000

Data Index: 364617 (C4 (Web Text))

Max Activating Token Index: 422

Text #5

Max Range: 0.6321. Min Range: -0.6321

Max Act: 0.4396. Min Act: -0.0000

Data Index: 1268055 (C4 (Web Text))

Max Activating Token Index: 651

Text #6

Max Range: 0.6321. Min Range: -0.6321

Max Act: 0.4246. Min Act: -0.0000

Data Index: 1563661 (Python Code)

Max Activating Token Index: 181

Text #7

Max Range: 0.6321. Min Range: -0.6321

Max Act: 0.3997. Min Act: -0.0000

Data Index: 1114637 (C4 (Web Text))

Max Activating Token Index: 634

Text #8

Max Range: 0.6321. Min Range: -0.6321

Max Act: 0.4010. Min Act: -0.0000

Data Index: 491227 (C4 (Web Text))

Max Activating Token Index: 682

Text #9

Max Range: 0.6321. Min Range: -0.6321

Max Act: 0.4161. Min Act: -0.0000

Data Index: 1612786 (Python Code)

Max Activating Token Index: 521

Text #10

Max Range: 0.6321. Min Range: -0.6321

Max Act: 0.4134. Min Act: -0.0000

Data Index: 1393068 (Python Code)

Max Activating Token Index: 967

Text #11

Max Range: 0.6321. Min Range: -0.6321

Max Act: 0.4099. Min Act: -0.0000

Data Index: 244198 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 0.6321. Min Range: -0.6321

Max Act: 0.3936. Min Act: -0.0000

Data Index: 1379732 (Python Code)

Max Activating Token Index: 807

Text #13

Max Range: 0.6321. Min Range: -0.6321

Max Act: 0.4060. Min Act: -0.0000

Data Index: 1645157 (Python Code)

Max Activating Token Index: 876

Text #14

Max Range: 0.6321. Min Range: -0.6321

Max Act: 0.4033. Min Act: -0.0000

Data Index: 1015706 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 0.6321. Min Range: -0.6321

Max Act: 0.3885. Min Act: -0.0000

Data Index: 1620540 (Python Code)

Max Activating Token Index: 353

Text #16

Max Range: 0.6321. Min Range: -0.6321

Max Act: 0.3998. Min Act: -0.0000

Data Index: 687601 (C4 (Web Text))

Max Activating Token Index: 261

Text #17

Max Range: 0.6321. Min Range: -0.6321

Max Act: 0.3861. Min Act: -0.0000

Data Index: 1579892 (Python Code)

Max Activating Token Index: 908

Text #18

Max Range: 0.6321. Min Range: -0.6321

Max Act: 0.3958. Min Act: -0.0000

Data Index: 1171212 (C4 (Web Text))

Max Activating Token Index: 537

Text #19

Max Range: 0.6321. Min Range: -0.6321

Max Act: 0.3973. Min Act: -0.0000

Data Index: 696749 (C4 (Web Text))

Max Activating Token Index: 863