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

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

Neuron 3134 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: 0.6249. Min Range: -0.6249

Max Act: 0.6249. Min Act: -0.0000

Data Index: 912932 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.6055. Min Act: -0.0000

Data Index: 675278 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5508. Min Act: -0.0000

Data Index: 346475 (C4 (Web Text))

Max Activating Token Index: 806

Text #3

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5340. Min Act: -0.0000

Data Index: 846200 (C4 (Web Text))

Max Activating Token Index: 859

Text #4

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5039. Min Act: -0.0000

Data Index: 371906 (C4 (Web Text))

Max Activating Token Index: 585

Text #5

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4957. Min Act: -0.0000

Data Index: 1292486 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4923. Min Act: -0.0000

Data Index: 599650 (C4 (Web Text))

Max Activating Token Index: 897

Text #7

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4759. Min Act: -0.0000

Data Index: 17516 (C4 (Web Text))

Max Activating Token Index: 477

Text #8

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4918. Min Act: -0.0000

Data Index: 579443 (C4 (Web Text))

Max Activating Token Index: 441

Text #9

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4467. Min Act: -0.0000

Data Index: 569854 (C4 (Web Text))

Max Activating Token Index: 520

Text #10

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4488. Min Act: -0.0000

Data Index: 192402 (C4 (Web Text))

Max Activating Token Index: 286

Text #11

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4510. Min Act: -0.0000

Data Index: 1220757 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4512. Min Act: -0.0000

Data Index: 488561 (C4 (Web Text))

Max Activating Token Index: 985

Text #13

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4621. Min Act: -0.0000

Data Index: 1135411 (C4 (Web Text))

Max Activating Token Index: 221

Text #14

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4301. Min Act: -0.0000

Data Index: 992335 (C4 (Web Text))

Max Activating Token Index: 236

Text #15

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5015. Min Act: -0.0000

Data Index: 1171828 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4317. Min Act: -0.0000

Data Index: 299026 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4134. Min Act: -0.0000

Data Index: 1173029 (C4 (Web Text))

Max Activating Token Index: 759

Text #18

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4413. Min Act: -0.0000

Data Index: 272732 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4109. Min Act: -0.0000

Data Index: 224217 (C4 (Web Text))

Max Activating Token Index: 691