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

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

Neuron 1098 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0326. Min Range: -1.0326

Max Act: 1.0326. Min Act: -0.0000

Data Index: 549991 (C4 (Web Text))

Max Activating Token Index: 465

Text #1

Max Range: 1.0326. Min Range: -1.0326

Max Act: 0.9210. Min Act: -0.0000

Data Index: 885506 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 1.0326. Min Range: -1.0326

Max Act: 0.9693. Min Act: -0.0000

Data Index: 205439 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 1.0326. Min Range: -1.0326

Max Act: 0.8626. Min Act: -0.0000

Data Index: 1085175 (C4 (Web Text))

Max Activating Token Index: 361

Text #4

Max Range: 1.0326. Min Range: -1.0326

Max Act: 0.9158. Min Act: -0.0000

Data Index: 406890 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 1.0326. Min Range: -1.0326

Max Act: 0.8373. Min Act: -0.0000

Data Index: 492201 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 1.0326. Min Range: -1.0326

Max Act: 0.8269. Min Act: -0.0000

Data Index: 309111 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 1.0326. Min Range: -1.0326

Max Act: 0.7883. Min Act: -0.0000

Data Index: 1347245 (C4 (Web Text))

Max Activating Token Index: 430

Text #8

Max Range: 1.0326. Min Range: -1.0326

Max Act: 0.7638. Min Act: -0.0000

Data Index: 1226712 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 1.0326. Min Range: -1.0326

Max Act: 0.7280. Min Act: -0.0000

Data Index: 1173304 (C4 (Web Text))

Max Activating Token Index: 748

Text #10

Max Range: 1.0326. Min Range: -1.0326

Max Act: 0.7652. Min Act: -0.0000

Data Index: 898524 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 1.0326. Min Range: -1.0326

Max Act: 0.7211. Min Act: -0.0000

Data Index: 406372 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 1.0326. Min Range: -1.0326

Max Act: 0.7424. Min Act: -0.0000

Data Index: 1242429 (C4 (Web Text))

Max Activating Token Index: 68

Text #13

Max Range: 1.0326. Min Range: -1.0326

Max Act: 0.7495. Min Act: -0.0000

Data Index: 36721 (C4 (Web Text))

Max Activating Token Index: 633

Text #14

Max Range: 1.0326. Min Range: -1.0326

Max Act: 0.7636. Min Act: -0.0000

Data Index: 1177470 (C4 (Web Text))

Max Activating Token Index: 1018

Text #15

Max Range: 1.0326. Min Range: -1.0326

Max Act: 0.7322. Min Act: -0.0000

Data Index: 753233 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 1.0326. Min Range: -1.0326

Max Act: 0.6863. Min Act: -0.0000

Data Index: 1615939 (Python Code)

Max Activating Token Index: 97

Text #17

Max Range: 1.0326. Min Range: -1.0326

Max Act: 0.7099. Min Act: -0.0000

Data Index: 987823 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 1.0326. Min Range: -1.0326

Max Act: 0.6831. Min Act: -0.0000

Data Index: 571509 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 1.0326. Min Range: -1.0326

Max Act: 0.6778. Min Act: -0.0000

Data Index: 80908 (C4 (Web Text))

Max Activating Token Index: 257