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

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

Neuron 4295 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: 3.2810. Min Range: -3.2810

Max Act: 3.2810. Min Act: -0.0000

Data Index: 1145778 (C4 (Web Text))

Max Activating Token Index: 1013

Text #1

Max Range: 3.2810. Min Range: -3.2810

Max Act: 3.2680. Min Act: -0.0000

Data Index: 1072687 (C4 (Web Text))

Max Activating Token Index: 630

Text #2

Max Range: 3.2810. Min Range: -3.2810

Max Act: 3.0630. Min Act: -0.0000

Data Index: 1324554 (C4 (Web Text))

Max Activating Token Index: 1002

Text #3

Max Range: 3.2810. Min Range: -3.2810

Max Act: 2.8257. Min Act: -0.0000

Data Index: 236675 (C4 (Web Text))

Max Activating Token Index: 946

Text #4

Max Range: 3.2810. Min Range: -3.2810

Max Act: 2.7682. Min Act: -0.0000

Data Index: 615874 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 3.2810. Min Range: -3.2810

Max Act: 2.6973. Min Act: -0.0000

Data Index: 424338 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 3.2810. Min Range: -3.2810

Max Act: 2.8327. Min Act: -0.0000

Data Index: 713622 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 3.2810. Min Range: -3.2810

Max Act: 2.8078. Min Act: -0.0000

Data Index: 759595 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 3.2810. Min Range: -3.2810

Max Act: 2.8018. Min Act: -0.0000

Data Index: 222536 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 3.2810. Min Range: -3.2810

Max Act: 3.0893. Min Act: -0.0000

Data Index: 418549 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 3.2810. Min Range: -3.2810

Max Act: 2.7798. Min Act: -0.0000

Data Index: 324267 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 3.2810. Min Range: -3.2810

Max Act: 2.7468. Min Act: -0.0000

Data Index: 968503 (C4 (Web Text))

Max Activating Token Index: 440

Text #12

Max Range: 3.2810. Min Range: -3.2810

Max Act: 2.7523. Min Act: -0.0000

Data Index: 237390 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 3.2810. Min Range: -3.2810

Max Act: 2.6687. Min Act: -0.0000

Data Index: 877410 (C4 (Web Text))

Max Activating Token Index: 118

Text #14

Max Range: 3.2810. Min Range: -3.2810

Max Act: 2.5229. Min Act: -0.0000

Data Index: 106193 (C4 (Web Text))

Max Activating Token Index: 134

Text #15

Max Range: 3.2810. Min Range: -3.2810

Max Act: 2.4939. Min Act: -0.0000

Data Index: 120224 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 3.2810. Min Range: -3.2810

Max Act: 2.5962. Min Act: -0.0000

Data Index: 1097186 (C4 (Web Text))

Max Activating Token Index: 803

Text #17

Max Range: 3.2810. Min Range: -3.2810

Max Act: 2.4375. Min Act: -0.0000

Data Index: 766973 (C4 (Web Text))

Max Activating Token Index: 763

Text #18

Max Range: 3.2810. Min Range: -3.2810

Max Act: 2.5514. Min Act: -0.0000

Data Index: 43548 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 3.2810. Min Range: -3.2810

Max Act: 2.5744. Min Act: -0.0000

Data Index: 884494 (C4 (Web Text))

Max Activating Token Index: 256