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

Dataset: The Pile

Neuron 4387 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6103. Min Range: -3.6103

Max Act: 3.6103. Min Act: -0.0000

Data Index: 58730 (The Pile)

Max Activating Token Index: 841

Text #1

Max Range: 3.6103. Min Range: -3.6103

Max Act: 3.0840. Min Act: -0.0000

Data Index: 1926628 (The Pile)

Max Activating Token Index: 743

Text #2

Max Range: 3.6103. Min Range: -3.6103

Max Act: 2.9091. Min Act: -0.0000

Data Index: 267112 (The Pile)

Max Activating Token Index: 102

Text #3

Max Range: 3.6103. Min Range: -3.6103

Max Act: 3.0489. Min Act: -0.0000

Data Index: 1015113 (The Pile)

Max Activating Token Index: 910

Text #4

Max Range: 3.6103. Min Range: -3.6103

Max Act: 3.1822. Min Act: -0.0000

Data Index: 1154759 (The Pile)

Max Activating Token Index: 720

Text #5

Max Range: 3.6103. Min Range: -3.6103

Max Act: 3.0205. Min Act: -0.0000

Data Index: 1629054 (The Pile)

Max Activating Token Index: 667

Text #6

Max Range: 3.6103. Min Range: -3.6103

Max Act: 3.1182. Min Act: -0.0000

Data Index: 1356987 (The Pile)

Max Activating Token Index: 927

Text #7

Max Range: 3.6103. Min Range: -3.6103

Max Act: 2.9560. Min Act: -0.0000

Data Index: 263126 (The Pile)

Max Activating Token Index: 31

Text #8

Max Range: 3.6103. Min Range: -3.6103

Max Act: 3.0283. Min Act: -0.0000

Data Index: 1370774 (The Pile)

Max Activating Token Index: 888

Text #9

Max Range: 3.6103. Min Range: -3.6103

Max Act: 2.8889. Min Act: -0.0000

Data Index: 859546 (The Pile)

Max Activating Token Index: 141

Text #10

Max Range: 3.6103. Min Range: -3.6103

Max Act: 2.8762. Min Act: -0.0000

Data Index: 477202 (The Pile)

Max Activating Token Index: 10

Text #11

Max Range: 3.6103. Min Range: -3.6103

Max Act: 3.0168. Min Act: 0.0000

Data Index: 588699 (The Pile)

Max Activating Token Index: 41

Text #12

Max Range: 3.6103. Min Range: -3.6103

Max Act: 2.9238. Min Act: -0.0000

Data Index: 1583390 (The Pile)

Max Activating Token Index: 418

Text #13

Max Range: 3.6103. Min Range: -3.6103

Max Act: 2.5988. Min Act: -0.0000

Data Index: 1796702 (The Pile)

Max Activating Token Index: 203

Text #14

Max Range: 3.6103. Min Range: -3.6103

Max Act: 2.3441. Min Act: -0.0000

Data Index: 380363 (The Pile)

Max Activating Token Index: 78

Text #15

Max Range: 3.6103. Min Range: -3.6103

Max Act: 2.8158. Min Act: -0.0000

Data Index: 876174 (The Pile)

Max Activating Token Index: 137

Text #16

Max Range: 3.6103. Min Range: -3.6103

Max Act: 2.8152. Min Act: -0.0000

Data Index: 1604585 (The Pile)

Max Activating Token Index: 941

Text #17

Max Range: 3.6103. Min Range: -3.6103

Max Act: 2.6613. Min Act: -0.0000

Data Index: 1117036 (The Pile)

Max Activating Token Index: 296

Text #18

Max Range: 3.6103. Min Range: -3.6103

Max Act: 2.7958. Min Act: -0.0000

Data Index: 870687 (The Pile)

Max Activating Token Index: 408

Text #19

Max Range: 3.6103. Min Range: -3.6103

Max Act: 2.6517. Min Act: -0.0000

Data Index: 1201377 (The Pile)

Max Activating Token Index: 256