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

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

Neuron 2094 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.6312. Min Range: -6.6312

Max Act: 6.6312. Min Act: -0.0000

Data Index: 860169 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 6.6312. Min Range: -6.6312

Max Act: 6.3598. Min Act: -0.0000

Data Index: 480031 (C4 (Web Text))

Max Activating Token Index: 666

Text #2

Max Range: 6.6312. Min Range: -6.6312

Max Act: 6.1625. Min Act: -0.0000

Data Index: 400785 (C4 (Web Text))

Max Activating Token Index: 309

Text #3

Max Range: 6.6312. Min Range: -6.6312

Max Act: 6.1607. Min Act: -0.0000

Data Index: 109408 (C4 (Web Text))

Max Activating Token Index: 586

Text #4

Max Range: 6.6312. Min Range: -6.6312

Max Act: 6.1464. Min Act: -0.0000

Data Index: 429290 (C4 (Web Text))

Max Activating Token Index: 266

Text #5

Max Range: 6.6312. Min Range: -6.6312

Max Act: 5.9848. Min Act: -0.0000

Data Index: 1160396 (C4 (Web Text))

Max Activating Token Index: 498

Text #6

Max Range: 6.6312. Min Range: -6.6312

Max Act: 5.7758. Min Act: -0.0000

Data Index: 304980 (C4 (Web Text))

Max Activating Token Index: 680

Text #7

Max Range: 6.6312. Min Range: -6.6312

Max Act: 5.8938. Min Act: -0.0000

Data Index: 646292 (C4 (Web Text))

Max Activating Token Index: 123

Text #8

Max Range: 6.6312. Min Range: -6.6312

Max Act: 5.6976. Min Act: -0.0000

Data Index: 1283893 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 6.6312. Min Range: -6.6312

Max Act: 5.6040. Min Act: -0.0000

Data Index: 1432964 (Python Code)

Max Activating Token Index: 438

Text #10

Max Range: 6.6312. Min Range: -6.6312

Max Act: 5.4041. Min Act: -0.0000

Data Index: 1423284 (Python Code)

Max Activating Token Index: 506

Text #11

Max Range: 6.6312. Min Range: -6.6312

Max Act: 5.3620. Min Act: -0.0000

Data Index: 1139854 (C4 (Web Text))

Max Activating Token Index: 499

Text #12

Max Range: 6.6312. Min Range: -6.6312

Max Act: 5.3371. Min Act: -0.0000

Data Index: 991191 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 6.6312. Min Range: -6.6312

Max Act: 5.2555. Min Act: -0.0000

Data Index: 498160 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 6.6312. Min Range: -6.6312

Max Act: 5.1757. Min Act: -0.0000

Data Index: 267506 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 6.6312. Min Range: -6.6312

Max Act: 5.2877. Min Act: -0.0000

Data Index: 948703 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 6.6312. Min Range: -6.6312

Max Act: 4.6726. Min Act: -0.0000

Data Index: 1593957 (Python Code)

Max Activating Token Index: 1001

Text #17

Max Range: 6.6312. Min Range: -6.6312

Max Act: 4.4676. Min Act: -0.0000

Data Index: 1588133 (Python Code)

Max Activating Token Index: 103

Text #18

Max Range: 6.6312. Min Range: -6.6312

Max Act: 3.5977. Min Act: -0.0000

Data Index: 746857 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 6.6312. Min Range: -6.6312

Max Act: 3.5785. Min Act: -0.0000

Data Index: 1151103 (C4 (Web Text))

Max Activating Token Index: 849