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

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

Neuron 1165 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6105. Min Range: -1.6105

Max Act: 1.6105. Min Act: -0.0001

Data Index: 501135 (C4 (Web Text))

Max Activating Token Index: 110

Text #1

Max Range: 1.6105. Min Range: -1.6105

Max Act: 1.5698. Min Act: -0.0000

Data Index: 430424 (C4 (Web Text))

Max Activating Token Index: 675

Text #2

Max Range: 1.6105. Min Range: -1.6105

Max Act: 1.5619. Min Act: -0.0000

Data Index: 564403 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 1.6105. Min Range: -1.6105

Max Act: 1.4514. Min Act: -0.0000

Data Index: 440655 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 1.6105. Min Range: -1.6105

Max Act: 1.5110. Min Act: -0.0000

Data Index: 889510 (C4 (Web Text))

Max Activating Token Index: 420

Text #5

Max Range: 1.6105. Min Range: -1.6105

Max Act: 1.4405. Min Act: -0.0000

Data Index: 1126980 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 1.6105. Min Range: -1.6105

Max Act: 1.3651. Min Act: -0.0001

Data Index: 76041 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 1.6105. Min Range: -1.6105

Max Act: 1.2741. Min Act: -0.0000

Data Index: 672657 (C4 (Web Text))

Max Activating Token Index: 991

Text #8

Max Range: 1.6105. Min Range: -1.6105

Max Act: 1.2628. Min Act: -0.0000

Data Index: 237594 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 1.6105. Min Range: -1.6105

Max Act: 1.3708. Min Act: -0.0001

Data Index: 407567 (C4 (Web Text))

Max Activating Token Index: 530

Text #10

Max Range: 1.6105. Min Range: -1.6105

Max Act: 1.3492. Min Act: -0.0000

Data Index: 103077 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 1.6105. Min Range: -1.6105

Max Act: 1.3387. Min Act: -0.0000

Data Index: 348300 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 1.6105. Min Range: -1.6105

Max Act: 1.4952. Min Act: -0.0000

Data Index: 1078680 (C4 (Web Text))

Max Activating Token Index: 166

Text #13

Max Range: 1.6105. Min Range: -1.6105

Max Act: 1.4174. Min Act: -0.0000

Data Index: 506120 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 1.6105. Min Range: -1.6105

Max Act: 1.2927. Min Act: -0.0000

Data Index: 741447 (C4 (Web Text))

Max Activating Token Index: 414

Text #15

Max Range: 1.6105. Min Range: -1.6105

Max Act: 1.3127. Min Act: -0.0000

Data Index: 781417 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 1.6105. Min Range: -1.6105

Max Act: 1.3095. Min Act: 0.0003

Data Index: 1221111 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 1.6105. Min Range: -1.6105

Max Act: 1.3381. Min Act: -0.0000

Data Index: 222463 (C4 (Web Text))

Max Activating Token Index: 556

Text #18

Max Range: 1.6105. Min Range: -1.6105

Max Act: 1.2554. Min Act: -0.0000

Data Index: 458774 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 1.6105. Min Range: -1.6105

Max Act: 1.3212. Min Act: -0.0000

Data Index: 733215 (C4 (Web Text))

Max Activating Token Index: 355