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

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

Neuron 1266 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3435. Min Range: -1.3435

Max Act: 1.3435. Min Act: -0.0000

Data Index: 942316 (C4 (Web Text))

Max Activating Token Index: 873

Text #1

Max Range: 1.3435. Min Range: -1.3435

Max Act: 1.0328. Min Act: -0.0000

Data Index: 167374 (C4 (Web Text))

Max Activating Token Index: 826

Text #2

Max Range: 1.3435. Min Range: -1.3435

Max Act: 1.1041. Min Act: -0.0000

Data Index: 129297 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 1.3435. Min Range: -1.3435

Max Act: 0.9810. Min Act: -0.0000

Data Index: 1074141 (C4 (Web Text))

Max Activating Token Index: 170

Text #4

Max Range: 1.3435. Min Range: -1.3435

Max Act: 1.1079. Min Act: -0.0000

Data Index: 27458 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 1.3435. Min Range: -1.3435

Max Act: 0.9619. Min Act: -0.0000

Data Index: 793130 (C4 (Web Text))

Max Activating Token Index: 748

Text #6

Max Range: 1.3435. Min Range: -1.3435

Max Act: 0.9688. Min Act: -0.0000

Data Index: 421876 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 1.3435. Min Range: -1.3435

Max Act: 0.9798. Min Act: -0.0000

Data Index: 522527 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 1.3435. Min Range: -1.3435

Max Act: 0.9143. Min Act: -0.0000

Data Index: 1081300 (C4 (Web Text))

Max Activating Token Index: 1018

Text #9

Max Range: 1.3435. Min Range: -1.3435

Max Act: 0.9304. Min Act: -0.0000

Data Index: 231822 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 1.3435. Min Range: -1.3435

Max Act: 0.9829. Min Act: -0.0000

Data Index: 1269884 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 1.3435. Min Range: -1.3435

Max Act: 0.9154. Min Act: -0.0000

Data Index: 1000682 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 1.3435. Min Range: -1.3435

Max Act: 0.9991. Min Act: -0.0000

Data Index: 717582 (C4 (Web Text))

Max Activating Token Index: 328

Text #13

Max Range: 1.3435. Min Range: -1.3435

Max Act: 0.9377. Min Act: -0.0000

Data Index: 1132305 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 1.3435. Min Range: -1.3435

Max Act: 0.9375. Min Act: -0.0000

Data Index: 546744 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 1.3435. Min Range: -1.3435

Max Act: 0.9044. Min Act: -0.0000

Data Index: 876334 (C4 (Web Text))

Max Activating Token Index: 244

Text #16

Max Range: 1.3435. Min Range: -1.3435

Max Act: 0.8784. Min Act: -0.0000

Data Index: 815022 (C4 (Web Text))

Max Activating Token Index: 658

Text #17

Max Range: 1.3435. Min Range: -1.3435

Max Act: 0.8442. Min Act: -0.0000

Data Index: 794392 (C4 (Web Text))

Max Activating Token Index: 741

Text #18

Max Range: 1.3435. Min Range: -1.3435

Max Act: 0.8978. Min Act: -0.0000

Data Index: 625836 (C4 (Web Text))

Max Activating Token Index: 482

Text #19

Max Range: 1.3435. Min Range: -1.3435

Max Act: 0.9173. Min Act: -0.0000

Data Index: 494769 (C4 (Web Text))

Max Activating Token Index: 58