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

Dataset: The Pile

Neuron 2902 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: 1.0527. Min Range: -1.0527

Max Act: 1.0527. Min Act: -0.0000

Data Index: 589729 (The Pile)

Max Activating Token Index: 13

Text #1

Max Range: 1.0527. Min Range: -1.0527

Max Act: 0.8420. Min Act: -0.0000

Data Index: 1260851 (The Pile)

Max Activating Token Index: 39

Text #2

Max Range: 1.0527. Min Range: -1.0527

Max Act: 0.8069. Min Act: -0.0000

Data Index: 1149151 (The Pile)

Max Activating Token Index: 362

Text #3

Max Range: 1.0527. Min Range: -1.0527

Max Act: 0.8022. Min Act: -0.0000

Data Index: 1602841 (The Pile)

Max Activating Token Index: 847

Text #4

Max Range: 1.0527. Min Range: -1.0527

Max Act: 0.7969. Min Act: -0.0000

Data Index: 1941680 (The Pile)

Max Activating Token Index: 832

Text #5

Max Range: 1.0527. Min Range: -1.0527

Max Act: 0.8124. Min Act: -0.0000

Data Index: 1269190 (The Pile)

Max Activating Token Index: 552

Text #6

Max Range: 1.0527. Min Range: -1.0527

Max Act: 0.7761. Min Act: -0.0000

Data Index: 642570 (The Pile)

Max Activating Token Index: 909

Text #7

Max Range: 1.0527. Min Range: -1.0527

Max Act: 0.7438. Min Act: -0.0000

Data Index: 449792 (The Pile)

Max Activating Token Index: 912

Text #8

Max Range: 1.0527. Min Range: -1.0527

Max Act: 0.8662. Min Act: -0.0000

Data Index: 1586192 (The Pile)

Max Activating Token Index: 21

Text #9

Max Range: 1.0527. Min Range: -1.0527

Max Act: 0.8093. Min Act: -0.0000

Data Index: 282260 (The Pile)

Max Activating Token Index: 561

Text #10

Max Range: 1.0527. Min Range: -1.0527

Max Act: 0.6951. Min Act: -0.0000

Data Index: 893435 (The Pile)

Max Activating Token Index: 132

Text #11

Max Range: 1.0527. Min Range: -1.0527

Max Act: 0.7554. Min Act: -0.0000

Data Index: 1047180 (The Pile)

Max Activating Token Index: 120

Text #12

Max Range: 1.0527. Min Range: -1.0527

Max Act: 0.7714. Min Act: -0.0000

Data Index: 538623 (The Pile)

Max Activating Token Index: 400

Text #13

Max Range: 1.0527. Min Range: -1.0527

Max Act: 0.6910. Min Act: -0.0000

Data Index: 713226 (The Pile)

Max Activating Token Index: 36

Text #14

Max Range: 1.0527. Min Range: -1.0527

Max Act: 0.7322. Min Act: -0.0000

Data Index: 632057 (The Pile)

Max Activating Token Index: 459

Text #15

Max Range: 1.0527. Min Range: -1.0527

Max Act: 0.7481. Min Act: -0.0000

Data Index: 1759044 (The Pile)

Max Activating Token Index: 118

Text #16

Max Range: 1.0527. Min Range: -1.0527

Max Act: 0.7026. Min Act: -0.0000

Data Index: 1699913 (The Pile)

Max Activating Token Index: 766

Text #17

Max Range: 1.0527. Min Range: -1.0527

Max Act: 0.7136. Min Act: -0.0000

Data Index: 1493533 (The Pile)

Max Activating Token Index: 244

Text #18

Max Range: 1.0527. Min Range: -1.0527

Max Act: 0.6922. Min Act: -0.0000

Data Index: 978010 (The Pile)

Max Activating Token Index: 69

Text #19

Max Range: 1.0527. Min Range: -1.0527

Max Act: 0.7069. Min Act: -0.0000

Data Index: 1582854 (The Pile)

Max Activating Token Index: 160