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

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

Neuron 465 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.8440. Min Act: -0.0000

Data Index: 1519262 (Python Code)

Max Activating Token Index: 117

Text #1

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.5660. Min Act: -0.0000

Data Index: 1449808 (Python Code)

Max Activating Token Index: 563

Text #2

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.5626. Min Act: -0.0000

Data Index: 1561526 (Python Code)

Max Activating Token Index: 64

Text #3

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.5091. Min Act: -0.0000

Data Index: 1532734 (Python Code)

Max Activating Token Index: 314

Text #4

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.5438. Min Act: -0.0000

Data Index: 1465156 (Python Code)

Max Activating Token Index: 142

Text #5

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.4586. Min Act: -0.0000

Data Index: 1597647 (Python Code)

Max Activating Token Index: 121

Text #6

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.4622. Min Act: -0.0000

Data Index: 1631747 (Python Code)

Max Activating Token Index: 962

Text #7

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.4377. Min Act: -0.0000

Data Index: 1531421 (Python Code)

Max Activating Token Index: 190

Text #8

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.4140. Min Act: -0.0000

Data Index: 1585481 (Python Code)

Max Activating Token Index: 563

Text #9

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.4442. Min Act: -0.0000

Data Index: 1474701 (Python Code)

Max Activating Token Index: 275

Text #10

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.3890. Min Act: -0.0000

Data Index: 1517247 (Python Code)

Max Activating Token Index: 104

Text #11

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.3876. Min Act: -0.0000

Data Index: 1355257 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.4233. Min Act: -0.0000

Data Index: 1425727 (Python Code)

Max Activating Token Index: 74

Text #13

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.4198. Min Act: -0.0000

Data Index: 231178 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.3822. Min Act: -0.0000

Data Index: 1396787 (Python Code)

Max Activating Token Index: 92

Text #15

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.3740. Min Act: -0.0000

Data Index: 1575750 (Python Code)

Max Activating Token Index: 209

Text #16

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.3859. Min Act: -0.0000

Data Index: 1628717 (Python Code)

Max Activating Token Index: 74

Text #17

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.3724. Min Act: -0.0000

Data Index: 1654761 (Python Code)

Max Activating Token Index: 69

Text #18

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.3686. Min Act: -0.0000

Data Index: 1371698 (Python Code)

Max Activating Token Index: 188

Text #19

Max Range: 1.8440. Min Range: -1.8440

Max Act: 1.4080. Min Act: -0.0000

Data Index: 1407964 (Python Code)

Max Activating Token Index: 312