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

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

Neuron 3259 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3083. Min Range: -4.3083

Max Act: 4.3083. Min Act: -0.0000

Data Index: 564558 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 4.3083. Min Range: -4.3083

Max Act: 2.6785. Min Act: -0.0000

Data Index: 805170 (C4 (Web Text))

Max Activating Token Index: 295

Text #2

Max Range: 4.3083. Min Range: -4.3083

Max Act: 2.3850. Min Act: 0.0001

Data Index: 1389567 (Python Code)

Max Activating Token Index: 28

Text #3

Max Range: 4.3083. Min Range: -4.3083

Max Act: 2.2480. Min Act: -0.0000

Data Index: 1387525 (Python Code)

Max Activating Token Index: 12

Text #4

Max Range: 4.3083. Min Range: -4.3083

Max Act: 2.3060. Min Act: 0.0001

Data Index: 258448 (C4 (Web Text))

Max Activating Token Index: 1011

Text #5

Max Range: 4.3083. Min Range: -4.3083

Max Act: 2.4046. Min Act: 0.0001

Data Index: 814687 (C4 (Web Text))

Max Activating Token Index: 977

Text #6

Max Range: 4.3083. Min Range: -4.3083

Max Act: 1.9605. Min Act: -0.0000

Data Index: 1493418 (Python Code)

Max Activating Token Index: 32

Text #7

Max Range: 4.3083. Min Range: -4.3083

Max Act: 1.8231. Min Act: 0.0000

Data Index: 407217 (C4 (Web Text))

Max Activating Token Index: 958

Text #8

Max Range: 4.3083. Min Range: -4.3083

Max Act: 1.8074. Min Act: -0.0000

Data Index: 1259936 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 4.3083. Min Range: -4.3083

Max Act: 1.8150. Min Act: -0.0000

Data Index: 32052 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 4.3083. Min Range: -4.3083

Max Act: 1.9030. Min Act: -0.0000

Data Index: 473572 (C4 (Web Text))

Max Activating Token Index: 619

Text #11

Max Range: 4.3083. Min Range: -4.3083

Max Act: 1.8250. Min Act: 0.0001

Data Index: 1582168 (Python Code)

Max Activating Token Index: 286

Text #12

Max Range: 4.3083. Min Range: -4.3083

Max Act: 1.8954. Min Act: -0.0000

Data Index: 1651592 (Python Code)

Max Activating Token Index: 73

Text #13

Max Range: 4.3083. Min Range: -4.3083

Max Act: 1.7673. Min Act: -0.0000

Data Index: 403703 (C4 (Web Text))

Max Activating Token Index: 278

Text #14

Max Range: 4.3083. Min Range: -4.3083

Max Act: 1.7103. Min Act: -0.0000

Data Index: 1342635 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 4.3083. Min Range: -4.3083

Max Act: 1.5848. Min Act: -0.0000

Data Index: 71015 (C4 (Web Text))

Max Activating Token Index: 538

Text #16

Max Range: 4.3083. Min Range: -4.3083

Max Act: 1.8225. Min Act: -0.0000

Data Index: 517544 (C4 (Web Text))

Max Activating Token Index: 477

Text #17

Max Range: 4.3083. Min Range: -4.3083

Max Act: 1.7308. Min Act: 0.0000

Data Index: 1470317 (Python Code)

Max Activating Token Index: 960

Text #18

Max Range: 4.3083. Min Range: -4.3083

Max Act: 1.7110. Min Act: -0.0000

Data Index: 1478684 (Python Code)

Max Activating Token Index: 583

Text #19

Max Range: 4.3083. Min Range: -4.3083

Max Act: 1.7759. Min Act: -0.0000

Data Index: 63079 (C4 (Web Text))

Max Activating Token Index: 511