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

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

Neuron 5092 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4146. Min Range: -1.4146

Max Act: 1.4041. Min Act: -0.0000

Data Index: 924277 (C4 (Web Text))

Max Activating Token Index: 250

Text #1

Max Range: 1.4146. Min Range: -1.4146

Max Act: 1.4146. Min Act: -0.0000

Data Index: 842037 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 1.4146. Min Range: -1.4146

Max Act: 1.1212. Min Act: -0.0000

Data Index: 918073 (C4 (Web Text))

Max Activating Token Index: 356

Text #3

Max Range: 1.4146. Min Range: -1.4146

Max Act: 1.2315. Min Act: -0.0000

Data Index: 371949 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 1.4146. Min Range: -1.4146

Max Act: 0.9769. Min Act: -0.0000

Data Index: 1223494 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 1.4146. Min Range: -1.4146

Max Act: 0.9733. Min Act: -0.0000

Data Index: 864554 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 1.4146. Min Range: -1.4146

Max Act: 1.0019. Min Act: -0.0000

Data Index: 381463 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 1.4146. Min Range: -1.4146

Max Act: 1.0023. Min Act: -0.0000

Data Index: 357246 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 1.4146. Min Range: -1.4146

Max Act: 0.9362. Min Act: -0.0000

Data Index: 1606172 (Python Code)

Max Activating Token Index: 423

Text #9

Max Range: 1.4146. Min Range: -1.4146

Max Act: 0.8063. Min Act: -0.0000

Data Index: 1360002 (Python Code)

Max Activating Token Index: 452

Text #10

Max Range: 1.4146. Min Range: -1.4146

Max Act: 0.8205. Min Act: -0.0000

Data Index: 1478904 (Python Code)

Max Activating Token Index: 801

Text #11

Max Range: 1.4146. Min Range: -1.4146

Max Act: 0.7492. Min Act: -0.0000

Data Index: 1489766 (Python Code)

Max Activating Token Index: 492

Text #12

Max Range: 1.4146. Min Range: -1.4146

Max Act: 0.6883. Min Act: -0.0000

Data Index: 1418132 (Python Code)

Max Activating Token Index: 931

Text #13

Max Range: 1.4146. Min Range: -1.4146

Max Act: 0.7110. Min Act: -0.0000

Data Index: 1570886 (Python Code)

Max Activating Token Index: 286

Text #14

Max Range: 1.4146. Min Range: -1.4146

Max Act: 0.7836. Min Act: -0.0000

Data Index: 524480 (C4 (Web Text))

Max Activating Token Index: 413

Text #15

Max Range: 1.4146. Min Range: -1.4146

Max Act: 0.7435. Min Act: -0.0000

Data Index: 30372 (C4 (Web Text))

Max Activating Token Index: 941

Text #16

Max Range: 1.4146. Min Range: -1.4146

Max Act: 0.7419. Min Act: -0.0000

Data Index: 831343 (C4 (Web Text))

Max Activating Token Index: 652

Text #17

Max Range: 1.4146. Min Range: -1.4146

Max Act: 0.6659. Min Act: -0.0000

Data Index: 1538312 (Python Code)

Max Activating Token Index: 773

Text #18

Max Range: 1.4146. Min Range: -1.4146

Max Act: 0.8045. Min Act: -0.0000

Data Index: 1578641 (Python Code)

Max Activating Token Index: 142

Text #19

Max Range: 1.4146. Min Range: -1.4146

Max Act: 0.6820. Min Act: -0.0000

Data Index: 1364490 (Python Code)

Max Activating Token Index: 947