Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 775 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.6749. Min Act: -0.0000

Data Index: 601707 (C4 (Web Text))

Max Activating Token Index: 239

Text #1

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.5387. Min Act: -0.0000

Data Index: 631467 (C4 (Web Text))

Max Activating Token Index: 935

Text #2

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.5082. Min Act: -0.0000

Data Index: 290379 (C4 (Web Text))

Max Activating Token Index: 504

Text #3

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.4671. Min Act: -0.0000

Data Index: 9683 (C4 (Web Text))

Max Activating Token Index: 848

Text #4

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.5079. Min Act: -0.0000

Data Index: 1646829 (Python Code)

Max Activating Token Index: 299

Text #5

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.4896. Min Act: -0.0000

Data Index: 915700 (C4 (Web Text))

Max Activating Token Index: 428

Text #6

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.4757. Min Act: -0.0000

Data Index: 1201047 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.4731. Min Act: -0.0000

Data Index: 602117 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.4893. Min Act: -0.0000

Data Index: 1054494 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.4748. Min Act: -0.0000

Data Index: 901841 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.4678. Min Act: -0.0000

Data Index: 1298442 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.4523. Min Act: -0.0000

Data Index: 592706 (C4 (Web Text))

Max Activating Token Index: 125

Text #12

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.4764. Min Act: -0.0000

Data Index: 1391274 (Python Code)

Max Activating Token Index: 498

Text #13

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.4719. Min Act: -0.0000

Data Index: 494239 (C4 (Web Text))

Max Activating Token Index: 780

Text #14

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.4554. Min Act: -0.0000

Data Index: 513555 (C4 (Web Text))

Max Activating Token Index: 927

Text #15

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.4342. Min Act: -0.0000

Data Index: 884852 (C4 (Web Text))

Max Activating Token Index: 711

Text #16

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.4362. Min Act: -0.0000

Data Index: 272950 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.4467. Min Act: -0.0000

Data Index: 393727 (C4 (Web Text))

Max Activating Token Index: 801

Text #18

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.4450. Min Act: -0.0000

Data Index: 1073114 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 0.6749. Min Range: -0.6749

Max Act: 0.4425. Min Act: -0.0000

Data Index: 1007066 (C4 (Web Text))

Max Activating Token Index: 51