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

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

Neuron 2538 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3277. Min Range: -1.3277

Max Act: 1.3277. Min Act: -0.0001

Data Index: 1528774 (Python Code)

Max Activating Token Index: 206

Text #1

Max Range: 1.3277. Min Range: -1.3277

Max Act: 1.2094. Min Act: -0.0001

Data Index: 1559040 (Python Code)

Max Activating Token Index: 36

Text #2

Max Range: 1.3277. Min Range: -1.3277

Max Act: 0.9638. Min Act: -0.0000

Data Index: 1641519 (Python Code)

Max Activating Token Index: 93

Text #3

Max Range: 1.3277. Min Range: -1.3277

Max Act: 0.9947. Min Act: -0.0001

Data Index: 1555683 (Python Code)

Max Activating Token Index: 57

Text #4

Max Range: 1.3277. Min Range: -1.3277

Max Act: 0.9615. Min Act: -0.0001

Data Index: 1647174 (Python Code)

Max Activating Token Index: 123

Text #5

Max Range: 1.3277. Min Range: -1.3277

Max Act: 0.9580. Min Act: -0.0001

Data Index: 798091 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 1.3277. Min Range: -1.3277

Max Act: 0.9537. Min Act: -0.0001

Data Index: 1022210 (C4 (Web Text))

Max Activating Token Index: 652

Text #7

Max Range: 1.3277. Min Range: -1.3277

Max Act: 0.8738. Min Act: -0.0001

Data Index: 1552231 (Python Code)

Max Activating Token Index: 109

Text #8

Max Range: 1.3277. Min Range: -1.3277

Max Act: 0.8763. Min Act: -0.0001

Data Index: 1392251 (Python Code)

Max Activating Token Index: 37

Text #9

Max Range: 1.3277. Min Range: -1.3277

Max Act: 0.9222. Min Act: -0.0001

Data Index: 1550315 (Python Code)

Max Activating Token Index: 58

Text #10

Max Range: 1.3277. Min Range: -1.3277

Max Act: 0.8920. Min Act: -0.0001

Data Index: 1457152 (Python Code)

Max Activating Token Index: 52

Text #11

Max Range: 1.3277. Min Range: -1.3277

Max Act: 0.8655. Min Act: -0.0001

Data Index: 160102 (C4 (Web Text))

Max Activating Token Index: 316

Text #12

Max Range: 1.3277. Min Range: -1.3277

Max Act: 0.7245. Min Act: -0.0001

Data Index: 955974 (C4 (Web Text))

Max Activating Token Index: 676

Text #13

Max Range: 1.3277. Min Range: -1.3277

Max Act: 0.8439. Min Act: -0.0001

Data Index: 1596385 (Python Code)

Max Activating Token Index: 171

Text #14

Max Range: 1.3277. Min Range: -1.3277

Max Act: 0.8369. Min Act: -0.0001

Data Index: 1493115 (Python Code)

Max Activating Token Index: 22

Text #15

Max Range: 1.3277. Min Range: -1.3277

Max Act: 0.8170. Min Act: -0.0001

Data Index: 1404889 (Python Code)

Max Activating Token Index: 136

Text #16

Max Range: 1.3277. Min Range: -1.3277

Max Act: 0.8137. Min Act: -0.0001

Data Index: 576696 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 1.3277. Min Range: -1.3277

Max Act: 0.7338. Min Act: -0.0001

Data Index: 1057768 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 1.3277. Min Range: -1.3277

Max Act: 0.7626. Min Act: -0.0001

Data Index: 700552 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 1.3277. Min Range: -1.3277

Max Act: 0.6044. Min Act: -0.0001

Data Index: 1023396 (C4 (Web Text))

Max Activating Token Index: 611