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

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

Neuron 3908 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: 2.1234. Min Range: -2.1234

Max Act: 2.1234. Min Act: -0.0000

Data Index: 729164 (C4 (Web Text))

Max Activating Token Index: 681

Text #1

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.9177. Min Act: -0.0000

Data Index: 594399 (C4 (Web Text))

Max Activating Token Index: 724

Text #2

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.7686. Min Act: -0.0000

Data Index: 162878 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.7907. Min Act: -0.0000

Data Index: 1367704 (Python Code)

Max Activating Token Index: 419

Text #4

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.7335. Min Act: -0.0000

Data Index: 1548426 (Python Code)

Max Activating Token Index: 833

Text #5

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.6276. Min Act: -0.0000

Data Index: 1415833 (Python Code)

Max Activating Token Index: 300

Text #6

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.7103. Min Act: -0.0000

Data Index: 1296083 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.6778. Min Act: -0.0000

Data Index: 464380 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.5618. Min Act: -0.0000

Data Index: 1652008 (Python Code)

Max Activating Token Index: 21

Text #9

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.6573. Min Act: -0.0000

Data Index: 1182503 (C4 (Web Text))

Max Activating Token Index: 162

Text #10

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.6840. Min Act: -0.0000

Data Index: 408579 (C4 (Web Text))

Max Activating Token Index: 262

Text #11

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.7651. Min Act: -0.0000

Data Index: 452116 (C4 (Web Text))

Max Activating Token Index: 849

Text #12

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.8666. Min Act: -0.0000

Data Index: 98023 (C4 (Web Text))

Max Activating Token Index: 236

Text #13

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.6166. Min Act: -0.0000

Data Index: 353788 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.6181. Min Act: -0.0000

Data Index: 442883 (C4 (Web Text))

Max Activating Token Index: 624

Text #15

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.5992. Min Act: -0.0000

Data Index: 47552 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.5992. Min Act: -0.0000

Data Index: 343976 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.5230. Min Act: -0.0000

Data Index: 689954 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.5645. Min Act: -0.0000

Data Index: 1123030 (C4 (Web Text))

Max Activating Token Index: 448

Text #19

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.5475. Min Act: -0.0000

Data Index: 1522681 (Python Code)

Max Activating Token Index: 560