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

Dataset: The Pile

Neuron 1899 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.4820. Min Act: -0.0000

Data Index: 1708386 (The Pile)

Max Activating Token Index: 989

Text #1

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.4069. Min Act: -0.0000

Data Index: 1439899 (The Pile)

Max Activating Token Index: 942

Text #2

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.3809. Min Act: -0.0000

Data Index: 1121945 (The Pile)

Max Activating Token Index: 360

Text #3

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.3779. Min Act: -0.0000

Data Index: 669202 (The Pile)

Max Activating Token Index: 105

Text #4

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.2846. Min Act: -0.0000

Data Index: 1107462 (The Pile)

Max Activating Token Index: 798

Text #5

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.3051. Min Act: -0.0000

Data Index: 1977407 (The Pile)

Max Activating Token Index: 1017

Text #6

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.3161. Min Act: -0.0000

Data Index: 981503 (The Pile)

Max Activating Token Index: 852

Text #7

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.2499. Min Act: -0.0000

Data Index: 220776 (The Pile)

Max Activating Token Index: 174

Text #8

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.2705. Min Act: -0.0000

Data Index: 1423191 (The Pile)

Max Activating Token Index: 542

Text #9

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.2840. Min Act: -0.0000

Data Index: 76508 (The Pile)

Max Activating Token Index: 145

Text #10

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.2573. Min Act: -0.0000

Data Index: 1918028 (The Pile)

Max Activating Token Index: 1011

Text #11

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.2757. Min Act: -0.0000

Data Index: 1923416 (The Pile)

Max Activating Token Index: 713

Text #12

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.2745. Min Act: -0.0000

Data Index: 588673 (The Pile)

Max Activating Token Index: 344

Text #13

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.2727. Min Act: -0.0000

Data Index: 746562 (The Pile)

Max Activating Token Index: 530

Text #14

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.2605. Min Act: -0.0000

Data Index: 651066 (The Pile)

Max Activating Token Index: 831

Text #15

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.2739. Min Act: -0.0000

Data Index: 1622802 (The Pile)

Max Activating Token Index: 1003

Text #16

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.2343. Min Act: -0.0000

Data Index: 1638547 (The Pile)

Max Activating Token Index: 723

Text #17

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.2559. Min Act: -0.0000

Data Index: 324962 (The Pile)

Max Activating Token Index: 902

Text #18

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.2489. Min Act: -0.0000

Data Index: 40582 (The Pile)

Max Activating Token Index: 50

Text #19

Max Range: 0.4820. Min Range: -0.4820

Max Act: 0.2606. Min Act: -0.0000

Data Index: 294853 (The Pile)

Max Activating Token Index: 469