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

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

Neuron 2454 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2965. Min Range: -3.2965

Max Act: 3.2965. Min Act: -0.0000

Data Index: 541527 (C4 (Web Text))

Max Activating Token Index: 879

Text #1

Max Range: 3.2965. Min Range: -3.2965

Max Act: 3.1730. Min Act: -0.0000

Data Index: 223995 (C4 (Web Text))

Max Activating Token Index: 409

Text #2

Max Range: 3.2965. Min Range: -3.2965

Max Act: 2.8287. Min Act: -0.0000

Data Index: 839493 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 3.2965. Min Range: -3.2965

Max Act: 2.5661. Min Act: -0.0000

Data Index: 554987 (C4 (Web Text))

Max Activating Token Index: 1018

Text #4

Max Range: 3.2965. Min Range: -3.2965

Max Act: 2.8054. Min Act: -0.0000

Data Index: 244977 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 3.2965. Min Range: -3.2965

Max Act: 2.6823. Min Act: -0.0000

Data Index: 1310801 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 3.2965. Min Range: -3.2965

Max Act: 2.4764. Min Act: -0.0000

Data Index: 1102235 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 3.2965. Min Range: -3.2965

Max Act: 2.5876. Min Act: -0.0000

Data Index: 1086455 (C4 (Web Text))

Max Activating Token Index: 963

Text #8

Max Range: 3.2965. Min Range: -3.2965

Max Act: 2.5792. Min Act: -0.0000

Data Index: 621473 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 3.2965. Min Range: -3.2965

Max Act: 2.5402. Min Act: -0.0000

Data Index: 1405517 (Python Code)

Max Activating Token Index: 800

Text #10

Max Range: 3.2965. Min Range: -3.2965

Max Act: 2.4434. Min Act: -0.0000

Data Index: 229743 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 3.2965. Min Range: -3.2965

Max Act: 2.4371. Min Act: -0.0000

Data Index: 1028584 (C4 (Web Text))

Max Activating Token Index: 30

Text #12

Max Range: 3.2965. Min Range: -3.2965

Max Act: 2.6816. Min Act: -0.0000

Data Index: 143357 (C4 (Web Text))

Max Activating Token Index: 749

Text #13

Max Range: 3.2965. Min Range: -3.2965

Max Act: 2.6627. Min Act: -0.0000

Data Index: 769051 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 3.2965. Min Range: -3.2965

Max Act: 2.5280. Min Act: -0.0000

Data Index: 576160 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 3.2965. Min Range: -3.2965

Max Act: 2.4156. Min Act: -0.0000

Data Index: 4232 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 3.2965. Min Range: -3.2965

Max Act: 2.5060. Min Act: -0.0000

Data Index: 367982 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 3.2965. Min Range: -3.2965

Max Act: 2.5084. Min Act: -0.0000

Data Index: 343056 (C4 (Web Text))

Max Activating Token Index: 501

Text #18

Max Range: 3.2965. Min Range: -3.2965

Max Act: 2.5167. Min Act: -0.0000

Data Index: 881088 (C4 (Web Text))

Max Activating Token Index: 74

Text #19

Max Range: 3.2965. Min Range: -3.2965

Max Act: 2.5011. Min Act: -0.0000

Data Index: 961184 (C4 (Web Text))

Max Activating Token Index: 914