Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3957 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2049. Min Range: -1.2049

Max Act: 1.2049. Min Act: -0.0001

Data Index: 900317 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 1.2049. Min Range: -1.2049

Max Act: 1.1034. Min Act: -0.0001

Data Index: 728919 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 1.2049. Min Range: -1.2049

Max Act: 1.1612. Min Act: -0.0001

Data Index: 589123 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 1.2049. Min Range: -1.2049

Max Act: 1.0751. Min Act: -0.0001

Data Index: 27290 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 1.2049. Min Range: -1.2049

Max Act: 1.1365. Min Act: -0.0001

Data Index: 732786 (C4 (Web Text))

Max Activating Token Index: 236

Text #5

Max Range: 1.2049. Min Range: -1.2049

Max Act: 0.9913. Min Act: -0.0001

Data Index: 386418 (C4 (Web Text))

Max Activating Token Index: 231

Text #6

Max Range: 1.2049. Min Range: -1.2049

Max Act: 1.0468. Min Act: -0.0001

Data Index: 133472 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 1.2049. Min Range: -1.2049

Max Act: 1.1788. Min Act: -0.0001

Data Index: 1325565 (C4 (Web Text))

Max Activating Token Index: 195

Text #8

Max Range: 1.2049. Min Range: -1.2049

Max Act: 0.9675. Min Act: -0.0001

Data Index: 968502 (C4 (Web Text))

Max Activating Token Index: 188

Text #9

Max Range: 1.2049. Min Range: -1.2049

Max Act: 1.0821. Min Act: -0.0001

Data Index: 787157 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 1.2049. Min Range: -1.2049

Max Act: 0.9784. Min Act: -0.0001

Data Index: 1233490 (C4 (Web Text))

Max Activating Token Index: 136

Text #11

Max Range: 1.2049. Min Range: -1.2049

Max Act: 0.9090. Min Act: -0.0001

Data Index: 289860 (C4 (Web Text))

Max Activating Token Index: 152

Text #12

Max Range: 1.2049. Min Range: -1.2049

Max Act: 0.8775. Min Act: -0.0001

Data Index: 864163 (C4 (Web Text))

Max Activating Token Index: 265

Text #13

Max Range: 1.2049. Min Range: -1.2049

Max Act: 1.0059. Min Act: -0.0001

Data Index: 884446 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 1.2049. Min Range: -1.2049

Max Act: 1.0420. Min Act: -0.0001

Data Index: 891330 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 1.2049. Min Range: -1.2049

Max Act: 0.9276. Min Act: -0.0001

Data Index: 575957 (C4 (Web Text))

Max Activating Token Index: 307

Text #16

Max Range: 1.2049. Min Range: -1.2049

Max Act: 0.9307. Min Act: -0.0001

Data Index: 280620 (C4 (Web Text))

Max Activating Token Index: 46

Text #17

Max Range: 1.2049. Min Range: -1.2049

Max Act: 0.9536. Min Act: -0.0001

Data Index: 1178305 (C4 (Web Text))

Max Activating Token Index: 915

Text #18

Max Range: 1.2049. Min Range: -1.2049

Max Act: 0.9468. Min Act: -0.0001

Data Index: 551677 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 1.2049. Min Range: -1.2049

Max Act: 0.9715. Min Act: -0.0001

Data Index: 664086 (C4 (Web Text))

Max Activating Token Index: 4