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

Dataset: The Pile

Neuron 2085 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.4195. Min Act: -0.0000

Data Index: 382467 (The Pile)

Max Activating Token Index: 786

Text #1

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.3368. Min Act: -0.0000

Data Index: 963171 (The Pile)

Max Activating Token Index: 487

Text #2

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.3475. Min Act: -0.0000

Data Index: 413442 (The Pile)

Max Activating Token Index: 885

Text #3

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.3255. Min Act: -0.0000

Data Index: 453157 (The Pile)

Max Activating Token Index: 492

Text #4

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.3205. Min Act: -0.0000

Data Index: 1597102 (The Pile)

Max Activating Token Index: 987

Text #5

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.3148. Min Act: -0.0000

Data Index: 653209 (The Pile)

Max Activating Token Index: 389

Text #6

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.3252. Min Act: -0.0000

Data Index: 1996212 (The Pile)

Max Activating Token Index: 915

Text #7

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.3303. Min Act: -0.0000

Data Index: 266549 (The Pile)

Max Activating Token Index: 823

Text #8

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.3181. Min Act: -0.0000

Data Index: 1010162 (The Pile)

Max Activating Token Index: 333

Text #9

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.3093. Min Act: -0.0000

Data Index: 1317888 (The Pile)

Max Activating Token Index: 961

Text #10

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.3262. Min Act: -0.0000

Data Index: 881076 (The Pile)

Max Activating Token Index: 975

Text #11

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.3140. Min Act: -0.0000

Data Index: 1296244 (The Pile)

Max Activating Token Index: 783

Text #12

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.2931. Min Act: -0.0000

Data Index: 1645717 (The Pile)

Max Activating Token Index: 969

Text #13

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.2869. Min Act: -0.0000

Data Index: 520787 (The Pile)

Max Activating Token Index: 969

Text #14

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.2949. Min Act: -0.0000

Data Index: 1989131 (The Pile)

Max Activating Token Index: 286

Text #15

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.2845. Min Act: -0.0000

Data Index: 1007075 (The Pile)

Max Activating Token Index: 115

Text #16

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.2932. Min Act: -0.0000

Data Index: 26679 (The Pile)

Max Activating Token Index: 855

Text #17

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.2860. Min Act: -0.0000

Data Index: 1985074 (The Pile)

Max Activating Token Index: 854

Text #18

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.2765. Min Act: -0.0000

Data Index: 1849451 (The Pile)

Max Activating Token Index: 46

Text #19

Max Range: 0.4195. Min Range: -0.4195

Max Act: 0.2662. Min Act: -0.0000

Data Index: 143449 (The Pile)

Max Activating Token Index: 1021