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

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

Neuron 5722 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: 3.7672. Min Range: -3.7672

Max Act: 3.7672. Min Act: -0.0000

Data Index: 1332949 (C4 (Web Text))

Max Activating Token Index: 882

Text #1

Max Range: 3.7672. Min Range: -3.7672

Max Act: 3.1330. Min Act: -0.0000

Data Index: 367332 (C4 (Web Text))

Max Activating Token Index: 736

Text #2

Max Range: 3.7672. Min Range: -3.7672

Max Act: 3.2713. Min Act: -0.0000

Data Index: 88072 (C4 (Web Text))

Max Activating Token Index: 802

Text #3

Max Range: 3.7672. Min Range: -3.7672

Max Act: 2.9610. Min Act: -0.0000

Data Index: 318436 (C4 (Web Text))

Max Activating Token Index: 1013

Text #4

Max Range: 3.7672. Min Range: -3.7672

Max Act: 3.0456. Min Act: -0.0000

Data Index: 1271077 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 3.7672. Min Range: -3.7672

Max Act: 3.0104. Min Act: -0.0000

Data Index: 584402 (C4 (Web Text))

Max Activating Token Index: 726

Text #6

Max Range: 3.7672. Min Range: -3.7672

Max Act: 3.2797. Min Act: -0.0000

Data Index: 583255 (C4 (Web Text))

Max Activating Token Index: 756

Text #7

Max Range: 3.7672. Min Range: -3.7672

Max Act: 2.9479. Min Act: -0.0000

Data Index: 667037 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 3.7672. Min Range: -3.7672

Max Act: 2.9463. Min Act: -0.0000

Data Index: 332107 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 3.7672. Min Range: -3.7672

Max Act: 2.8878. Min Act: -0.0000

Data Index: 402296 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 3.7672. Min Range: -3.7672

Max Act: 2.8942. Min Act: -0.0000

Data Index: 60438 (C4 (Web Text))

Max Activating Token Index: 721

Text #11

Max Range: 3.7672. Min Range: -3.7672

Max Act: 2.7533. Min Act: -0.0000

Data Index: 655542 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 3.7672. Min Range: -3.7672

Max Act: 2.8942. Min Act: -0.0000

Data Index: 589396 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 3.7672. Min Range: -3.7672

Max Act: 2.8541. Min Act: -0.0000

Data Index: 972378 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 3.7672. Min Range: -3.7672

Max Act: 2.7907. Min Act: -0.0000

Data Index: 613300 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 3.7672. Min Range: -3.7672

Max Act: 2.6995. Min Act: -0.0000

Data Index: 116931 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 3.7672. Min Range: -3.7672

Max Act: 2.7088. Min Act: -0.0000

Data Index: 1168304 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 3.7672. Min Range: -3.7672

Max Act: 2.5970. Min Act: -0.0000

Data Index: 673742 (C4 (Web Text))

Max Activating Token Index: 673

Text #18

Max Range: 3.7672. Min Range: -3.7672

Max Act: 2.7052. Min Act: -0.0000

Data Index: 19441 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 3.7672. Min Range: -3.7672

Max Act: 2.6971. Min Act: -0.0000

Data Index: 1077984 (C4 (Web Text))

Max Activating Token Index: 635