Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2408 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1101. Min Range: -1.1101

Max Act: 1.1101. Min Act: -0.0001

Data Index: 1562589 (Python Code)

Max Activating Token Index: 164

Text #1

Max Range: 1.1101. Min Range: -1.1101

Max Act: 0.9140. Min Act: -0.0001

Data Index: 1447392 (Python Code)

Max Activating Token Index: 616

Text #2

Max Range: 1.1101. Min Range: -1.1101

Max Act: 0.8581. Min Act: -0.0001

Data Index: 1459737 (Python Code)

Max Activating Token Index: 422

Text #3

Max Range: 1.1101. Min Range: -1.1101

Max Act: 0.8967. Min Act: -0.0001

Data Index: 1518633 (Python Code)

Max Activating Token Index: 85

Text #4

Max Range: 1.1101. Min Range: -1.1101

Max Act: 0.7998. Min Act: -0.0001

Data Index: 1371196 (Python Code)

Max Activating Token Index: 816

Text #5

Max Range: 1.1101. Min Range: -1.1101

Max Act: 0.6064. Min Act: -0.0001

Data Index: 1548227 (Python Code)

Max Activating Token Index: 773

Text #6

Max Range: 1.1101. Min Range: -1.1101

Max Act: 0.7541. Min Act: -0.0001

Data Index: 1601224 (Python Code)

Max Activating Token Index: 172

Text #7

Max Range: 1.1101. Min Range: -1.1101

Max Act: 0.7476. Min Act: -0.0001

Data Index: 1533355 (Python Code)

Max Activating Token Index: 947

Text #8

Max Range: 1.1101. Min Range: -1.1101

Max Act: 0.6792. Min Act: -0.0001

Data Index: 1604599 (Python Code)

Max Activating Token Index: 600

Text #9

Max Range: 1.1101. Min Range: -1.1101

Max Act: 0.7004. Min Act: -0.0001

Data Index: 1552639 (Python Code)

Max Activating Token Index: 297

Text #10

Max Range: 1.1101. Min Range: -1.1101

Max Act: 0.5937. Min Act: -0.0001

Data Index: 1414022 (Python Code)

Max Activating Token Index: 799

Text #11

Max Range: 1.1101. Min Range: -1.1101

Max Act: 0.6933. Min Act: -0.0001

Data Index: 1402694 (Python Code)

Max Activating Token Index: 142

Text #12

Max Range: 1.1101. Min Range: -1.1101

Max Act: 0.6566. Min Act: -0.0001

Data Index: 1367849 (Python Code)

Max Activating Token Index: 953

Text #13

Max Range: 1.1101. Min Range: -1.1101

Max Act: 0.6200. Min Act: -0.0001

Data Index: 1398182 (Python Code)

Max Activating Token Index: 82

Text #14

Max Range: 1.1101. Min Range: -1.1101

Max Act: 0.6363. Min Act: -0.0001

Data Index: 1439525 (Python Code)

Max Activating Token Index: 988

Text #15

Max Range: 1.1101. Min Range: -1.1101

Max Act: 0.6008. Min Act: -0.0001

Data Index: 1490982 (Python Code)

Max Activating Token Index: 162

Text #16

Max Range: 1.1101. Min Range: -1.1101

Max Act: 0.6569. Min Act: -0.0001

Data Index: 1480737 (Python Code)

Max Activating Token Index: 20

Text #17

Max Range: 1.1101. Min Range: -1.1101

Max Act: 0.6117. Min Act: -0.0000

Data Index: 1479788 (Python Code)

Max Activating Token Index: 787

Text #18

Max Range: 1.1101. Min Range: -1.1101

Max Act: 0.6553. Min Act: -0.0001

Data Index: 1421318 (Python Code)

Max Activating Token Index: 630

Text #19

Max Range: 1.1101. Min Range: -1.1101

Max Act: 0.6271. Min Act: -0.0000

Data Index: 1429351 (Python Code)

Max Activating Token Index: 62