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

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

Neuron 747 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: 0.3050. Min Range: -0.3050

Max Act: 0.3050. Min Act: -0.0000

Data Index: 1320606 (C4 (Web Text))

Max Activating Token Index: 817

Text #1

Max Range: 0.3050. Min Range: -0.3050

Max Act: 0.3040. Min Act: -0.0000

Data Index: 1253579 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 0.3050. Min Range: -0.3050

Max Act: 0.2787. Min Act: -0.0000

Data Index: 27811 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 0.3050. Min Range: -0.3050

Max Act: 0.2814. Min Act: -0.0000

Data Index: 1252396 (C4 (Web Text))

Max Activating Token Index: 453

Text #4

Max Range: 0.3050. Min Range: -0.3050

Max Act: 0.2709. Min Act: -0.0000

Data Index: 1062548 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 0.3050. Min Range: -0.3050

Max Act: 0.2677. Min Act: -0.0000

Data Index: 1152934 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 0.3050. Min Range: -0.3050

Max Act: 0.2617. Min Act: -0.0000

Data Index: 367777 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 0.3050. Min Range: -0.3050

Max Act: 0.2583. Min Act: -0.0000

Data Index: 48804 (C4 (Web Text))

Max Activating Token Index: 303

Text #8

Max Range: 0.3050. Min Range: -0.3050

Max Act: 0.2573. Min Act: -0.0000

Data Index: 455077 (C4 (Web Text))

Max Activating Token Index: 917

Text #9

Max Range: 0.3050. Min Range: -0.3050

Max Act: 0.2522. Min Act: -0.0000

Data Index: 881574 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 0.3050. Min Range: -0.3050

Max Act: 0.2488. Min Act: -0.0000

Data Index: 339373 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 0.3050. Min Range: -0.3050

Max Act: 0.2474. Min Act: -0.0000

Data Index: 146961 (C4 (Web Text))

Max Activating Token Index: 533

Text #12

Max Range: 0.3050. Min Range: -0.3050

Max Act: 0.2467. Min Act: -0.0000

Data Index: 425458 (C4 (Web Text))

Max Activating Token Index: 755

Text #13

Max Range: 0.3050. Min Range: -0.3050

Max Act: 0.2392. Min Act: -0.0000

Data Index: 1185757 (C4 (Web Text))

Max Activating Token Index: 238

Text #14

Max Range: 0.3050. Min Range: -0.3050

Max Act: 0.2450. Min Act: -0.0000

Data Index: 1136797 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 0.3050. Min Range: -0.3050

Max Act: 0.2248. Min Act: -0.0000

Data Index: 630427 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 0.3050. Min Range: -0.3050

Max Act: 0.2560. Min Act: -0.0000

Data Index: 948177 (C4 (Web Text))

Max Activating Token Index: 313

Text #17

Max Range: 0.3050. Min Range: -0.3050

Max Act: 0.2159. Min Act: -0.0000

Data Index: 1249220 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 0.3050. Min Range: -0.3050

Max Act: 0.2158. Min Act: -0.0000

Data Index: 275362 (C4 (Web Text))

Max Activating Token Index: 802

Text #19

Max Range: 0.3050. Min Range: -0.3050

Max Act: 0.2188. Min Act: -0.0000

Data Index: 1175789 (C4 (Web Text))

Max Activating Token Index: 175