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

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

Neuron 1827 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6900. Min Range: -1.6900

Max Act: 1.6900. Min Act: -0.0001

Data Index: 198460 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 1.6900. Min Range: -1.6900

Max Act: 1.6596. Min Act: -0.0000

Data Index: 672723 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 1.6900. Min Range: -1.6900

Max Act: 1.6026. Min Act: -0.0000

Data Index: 104031 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 1.6900. Min Range: -1.6900

Max Act: 1.5831. Min Act: -0.0000

Data Index: 332456 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 1.6900. Min Range: -1.6900

Max Act: 1.6252. Min Act: -0.0000

Data Index: 1306646 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 1.6900. Min Range: -1.6900

Max Act: 1.4078. Min Act: -0.0000

Data Index: 1082521 (C4 (Web Text))

Max Activating Token Index: 188

Text #6

Max Range: 1.6900. Min Range: -1.6900

Max Act: 1.4266. Min Act: -0.0000

Data Index: 1255089 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 1.6900. Min Range: -1.6900

Max Act: 1.4027. Min Act: -0.0001

Data Index: 164109 (C4 (Web Text))

Max Activating Token Index: 956

Text #8

Max Range: 1.6900. Min Range: -1.6900

Max Act: 1.3964. Min Act: -0.0000

Data Index: 108965 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 1.6900. Min Range: -1.6900

Max Act: 1.3777. Min Act: -0.0000

Data Index: 1158716 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 1.6900. Min Range: -1.6900

Max Act: 1.2907. Min Act: -0.0001

Data Index: 240239 (C4 (Web Text))

Max Activating Token Index: 415

Text #11

Max Range: 1.6900. Min Range: -1.6900

Max Act: 1.4414. Min Act: -0.0000

Data Index: 941504 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 1.6900. Min Range: -1.6900

Max Act: 1.3582. Min Act: -0.0000

Data Index: 1351059 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 1.6900. Min Range: -1.6900

Max Act: 1.3189. Min Act: -0.0001

Data Index: 610398 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 1.6900. Min Range: -1.6900

Max Act: 1.2318. Min Act: -0.0001

Data Index: 708389 (C4 (Web Text))

Max Activating Token Index: 378

Text #15

Max Range: 1.6900. Min Range: -1.6900

Max Act: 1.3719. Min Act: -0.0000

Data Index: 439628 (C4 (Web Text))

Max Activating Token Index: 336

Text #16

Max Range: 1.6900. Min Range: -1.6900

Max Act: 1.2103. Min Act: -0.0000

Data Index: 893593 (C4 (Web Text))

Max Activating Token Index: 564

Text #17

Max Range: 1.6900. Min Range: -1.6900

Max Act: 1.2814. Min Act: -0.0000

Data Index: 487803 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 1.6900. Min Range: -1.6900

Max Act: 1.2094. Min Act: -0.0000

Data Index: 108017 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 1.6900. Min Range: -1.6900

Max Act: 1.2266. Min Act: -0.0000

Data Index: 898187 (C4 (Web Text))

Max Activating Token Index: 857