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

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

Neuron 3659 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9888. Min Range: -1.9888

Max Act: 1.9888. Min Act: -0.0000

Data Index: 1026933 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 1.9888. Min Range: -1.9888

Max Act: 1.8054. Min Act: -0.0000

Data Index: 876242 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 1.9888. Min Range: -1.9888

Max Act: 1.6402. Min Act: -0.0000

Data Index: 590729 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 1.9888. Min Range: -1.9888

Max Act: 1.5900. Min Act: -0.0000

Data Index: 722009 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 1.9888. Min Range: -1.9888

Max Act: 1.5450. Min Act: -0.0000

Data Index: 791932 (C4 (Web Text))

Max Activating Token Index: 769

Text #5

Max Range: 1.9888. Min Range: -1.9888

Max Act: 1.4562. Min Act: -0.0000

Data Index: 734289 (C4 (Web Text))

Max Activating Token Index: 1006

Text #6

Max Range: 1.9888. Min Range: -1.9888

Max Act: 1.4381. Min Act: -0.0000

Data Index: 639311 (C4 (Web Text))

Max Activating Token Index: 776

Text #7

Max Range: 1.9888. Min Range: -1.9888

Max Act: 1.4369. Min Act: -0.0000

Data Index: 504089 (C4 (Web Text))

Max Activating Token Index: 947

Text #8

Max Range: 1.9888. Min Range: -1.9888

Max Act: 1.4904. Min Act: -0.0000

Data Index: 1151019 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 1.9888. Min Range: -1.9888

Max Act: 1.4294. Min Act: -0.0000

Data Index: 93572 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 1.9888. Min Range: -1.9888

Max Act: 1.3410. Min Act: -0.0000

Data Index: 542234 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 1.9888. Min Range: -1.9888

Max Act: 1.4413. Min Act: -0.0000

Data Index: 946407 (C4 (Web Text))

Max Activating Token Index: 521

Text #12

Max Range: 1.9888. Min Range: -1.9888

Max Act: 1.3636. Min Act: -0.0000

Data Index: 1116062 (C4 (Web Text))

Max Activating Token Index: 570

Text #13

Max Range: 1.9888. Min Range: -1.9888

Max Act: 1.2267. Min Act: -0.0000

Data Index: 34658 (C4 (Web Text))

Max Activating Token Index: 817

Text #14

Max Range: 1.9888. Min Range: -1.9888

Max Act: 1.2203. Min Act: -0.0000

Data Index: 520391 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 1.9888. Min Range: -1.9888

Max Act: 1.3166. Min Act: -0.0000

Data Index: 838878 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 1.9888. Min Range: -1.9888

Max Act: 1.2963. Min Act: -0.0000

Data Index: 1320261 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 1.9888. Min Range: -1.9888

Max Act: 1.2649. Min Act: -0.0000

Data Index: 375053 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 1.9888. Min Range: -1.9888

Max Act: 1.0702. Min Act: -0.0000

Data Index: 44124 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 1.9888. Min Range: -1.9888

Max Act: 1.1990. Min Act: -0.0000

Data Index: 474001 (C4 (Web Text))

Max Activating Token Index: 864