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

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

Neuron 533 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: 2.6136. Min Range: -2.6136

Max Act: 2.6136. Min Act: -0.0000

Data Index: 103731 (C4 (Web Text))

Max Activating Token Index: 290

Text #1

Max Range: 2.6136. Min Range: -2.6136

Max Act: 2.4222. Min Act: -0.0000

Data Index: 1128139 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 2.6136. Min Range: -2.6136

Max Act: 2.3399. Min Act: -0.0000

Data Index: 68097 (C4 (Web Text))

Max Activating Token Index: 229

Text #3

Max Range: 2.6136. Min Range: -2.6136

Max Act: 2.3353. Min Act: -0.0000

Data Index: 663970 (C4 (Web Text))

Max Activating Token Index: 6

Text #4

Max Range: 2.6136. Min Range: -2.6136

Max Act: 2.1305. Min Act: -0.0000

Data Index: 268339 (C4 (Web Text))

Max Activating Token Index: 9

Text #5

Max Range: 2.6136. Min Range: -2.6136

Max Act: 2.1923. Min Act: -0.0000

Data Index: 458126 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 2.6136. Min Range: -2.6136

Max Act: 2.1225. Min Act: -0.0000

Data Index: 391996 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 2.6136. Min Range: -2.6136

Max Act: 2.2358. Min Act: -0.0000

Data Index: 369907 (C4 (Web Text))

Max Activating Token Index: 600

Text #8

Max Range: 2.6136. Min Range: -2.6136

Max Act: 1.7607. Min Act: -0.0000

Data Index: 839787 (C4 (Web Text))

Max Activating Token Index: 384

Text #9

Max Range: 2.6136. Min Range: -2.6136

Max Act: 1.9005. Min Act: -0.0000

Data Index: 740201 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 2.6136. Min Range: -2.6136

Max Act: 1.8939. Min Act: -0.0000

Data Index: 826252 (C4 (Web Text))

Max Activating Token Index: 860

Text #11

Max Range: 2.6136. Min Range: -2.6136

Max Act: 1.9873. Min Act: -0.0000

Data Index: 209492 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 2.6136. Min Range: -2.6136

Max Act: 1.6971. Min Act: -0.0000

Data Index: 270593 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 2.6136. Min Range: -2.6136

Max Act: 1.6653. Min Act: -0.0000

Data Index: 1292134 (C4 (Web Text))

Max Activating Token Index: 935

Text #14

Max Range: 2.6136. Min Range: -2.6136

Max Act: 1.8630. Min Act: -0.0000

Data Index: 1069430 (C4 (Web Text))

Max Activating Token Index: 36

Text #15

Max Range: 2.6136. Min Range: -2.6136

Max Act: 1.7593. Min Act: -0.0000

Data Index: 1086929 (C4 (Web Text))

Max Activating Token Index: 685

Text #16

Max Range: 2.6136. Min Range: -2.6136

Max Act: 1.8470. Min Act: -0.0000

Data Index: 385567 (C4 (Web Text))

Max Activating Token Index: 811

Text #17

Max Range: 2.6136. Min Range: -2.6136

Max Act: 1.8090. Min Act: -0.0000

Data Index: 1441986 (Python Code)

Max Activating Token Index: 61

Text #18

Max Range: 2.6136. Min Range: -2.6136

Max Act: 1.7015. Min Act: -0.0000

Data Index: 199477 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 2.6136. Min Range: -2.6136

Max Act: 1.8084. Min Act: -0.0000

Data Index: 1214817 (C4 (Web Text))

Max Activating Token Index: 966