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

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

Neuron 3238 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2933. Min Range: -2.2933

Max Act: 2.2933. Min Act: -0.0000

Data Index: 563839 (C4 (Web Text))

Max Activating Token Index: 800

Text #1

Max Range: 2.2933. Min Range: -2.2933

Max Act: 2.1450. Min Act: -0.0000

Data Index: 1021581 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 2.2933. Min Range: -2.2933

Max Act: 1.9053. Min Act: -0.0000

Data Index: 258988 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 2.2933. Min Range: -2.2933

Max Act: 1.8710. Min Act: -0.0000

Data Index: 282612 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 2.2933. Min Range: -2.2933

Max Act: 1.9499. Min Act: -0.0000

Data Index: 95431 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 2.2933. Min Range: -2.2933

Max Act: 1.9349. Min Act: -0.0000

Data Index: 433147 (C4 (Web Text))

Max Activating Token Index: 911

Text #6

Max Range: 2.2933. Min Range: -2.2933

Max Act: 1.9403. Min Act: -0.0000

Data Index: 1198575 (C4 (Web Text))

Max Activating Token Index: 436

Text #7

Max Range: 2.2933. Min Range: -2.2933

Max Act: 1.8194. Min Act: -0.0000

Data Index: 416301 (C4 (Web Text))

Max Activating Token Index: 190

Text #8

Max Range: 2.2933. Min Range: -2.2933

Max Act: 1.9103. Min Act: -0.0000

Data Index: 347454 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 2.2933. Min Range: -2.2933

Max Act: 1.7977. Min Act: -0.0000

Data Index: 520768 (C4 (Web Text))

Max Activating Token Index: 306

Text #10

Max Range: 2.2933. Min Range: -2.2933

Max Act: 1.8660. Min Act: -0.0000

Data Index: 36208 (C4 (Web Text))

Max Activating Token Index: 402

Text #11

Max Range: 2.2933. Min Range: -2.2933

Max Act: 1.9812. Min Act: -0.0000

Data Index: 1300989 (C4 (Web Text))

Max Activating Token Index: 451

Text #12

Max Range: 2.2933. Min Range: -2.2933

Max Act: 1.9535. Min Act: -0.0000

Data Index: 841808 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 2.2933. Min Range: -2.2933

Max Act: 1.8185. Min Act: -0.0000

Data Index: 679132 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 2.2933. Min Range: -2.2933

Max Act: 1.8163. Min Act: -0.0000

Data Index: 1069106 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 2.2933. Min Range: -2.2933

Max Act: 1.6743. Min Act: -0.0000

Data Index: 589105 (C4 (Web Text))

Max Activating Token Index: 953

Text #16

Max Range: 2.2933. Min Range: -2.2933

Max Act: 1.7253. Min Act: -0.0000

Data Index: 538675 (C4 (Web Text))

Max Activating Token Index: 552

Text #17

Max Range: 2.2933. Min Range: -2.2933

Max Act: 1.7001. Min Act: -0.0000

Data Index: 1011978 (C4 (Web Text))

Max Activating Token Index: 879

Text #18

Max Range: 2.2933. Min Range: -2.2933

Max Act: 1.6138. Min Act: -0.0000

Data Index: 369576 (C4 (Web Text))

Max Activating Token Index: 790

Text #19

Max Range: 2.2933. Min Range: -2.2933

Max Act: 1.6778. Min Act: -0.0000

Data Index: 932476 (C4 (Web Text))

Max Activating Token Index: 464