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

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

Neuron 3956 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0643. Min Range: -4.0643

Max Act: 4.0643. Min Act: -0.0001

Data Index: 755090 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.8989. Min Act: -0.0001

Data Index: 1269054 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.6800. Min Act: -0.0001

Data Index: 945912 (C4 (Web Text))

Max Activating Token Index: 513

Text #3

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.9547. Min Act: -0.0001

Data Index: 355706 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.7485. Min Act: -0.0001

Data Index: 191396 (C4 (Web Text))

Max Activating Token Index: 389

Text #5

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.7835. Min Act: -0.0001

Data Index: 466783 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.7691. Min Act: -0.0001

Data Index: 12792 (C4 (Web Text))

Max Activating Token Index: 473

Text #7

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.7396. Min Act: -0.0001

Data Index: 504253 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 4.0643. Min Range: -4.0643

Max Act: 4.0030. Min Act: -0.0001

Data Index: 270570 (C4 (Web Text))

Max Activating Token Index: 348

Text #9

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.4471. Min Act: -0.0001

Data Index: 957992 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.6643. Min Act: -0.0001

Data Index: 1235285 (C4 (Web Text))

Max Activating Token Index: 407

Text #11

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.4154. Min Act: -0.0001

Data Index: 607963 (C4 (Web Text))

Max Activating Token Index: 681

Text #12

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.3699. Min Act: -0.0001

Data Index: 1258992 (C4 (Web Text))

Max Activating Token Index: 465

Text #13

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.6341. Min Act: -0.0001

Data Index: 49899 (C4 (Web Text))

Max Activating Token Index: 257

Text #14

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.1852. Min Act: -0.0001

Data Index: 739920 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.4470. Min Act: -0.0001

Data Index: 270549 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.3217. Min Act: -0.0001

Data Index: 770965 (C4 (Web Text))

Max Activating Token Index: 480

Text #17

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.1166. Min Act: -0.0001

Data Index: 1207469 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.5699. Min Act: -0.0001

Data Index: 1180759 (C4 (Web Text))

Max Activating Token Index: 493

Text #19

Max Range: 4.0643. Min Range: -4.0643

Max Act: 3.5622. Min Act: -0.0001

Data Index: 745292 (C4 (Web Text))

Max Activating Token Index: 587