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

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

Neuron 1903 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.1129. Min Act: -0.0002

Data Index: 1043023 (C4 (Web Text))

Max Activating Token Index: 236

Text #1

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0986. Min Act: -0.0002

Data Index: 1276943 (C4 (Web Text))

Max Activating Token Index: 588

Text #2

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.1082. Min Act: -0.0002

Data Index: 304027 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.1094. Min Act: -0.0002

Data Index: 386295 (C4 (Web Text))

Max Activating Token Index: 849

Text #4

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0955. Min Act: -0.0002

Data Index: 68956 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.1048. Min Act: -0.0002

Data Index: 676135 (C4 (Web Text))

Max Activating Token Index: 783

Text #6

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0983. Min Act: -0.0002

Data Index: 90613 (C4 (Web Text))

Max Activating Token Index: 85

Text #7

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0916. Min Act: -0.0002

Data Index: 623533 (C4 (Web Text))

Max Activating Token Index: 268

Text #8

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0942. Min Act: -0.0002

Data Index: 25080 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.1038. Min Act: -0.0002

Data Index: 770428 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0928. Min Act: -0.0002

Data Index: 1314315 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0795. Min Act: -0.0002

Data Index: 340653 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0884. Min Act: -0.0002

Data Index: 810292 (C4 (Web Text))

Max Activating Token Index: 199

Text #13

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0963. Min Act: -0.0002

Data Index: 136480 (C4 (Web Text))

Max Activating Token Index: 534

Text #14

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0883. Min Act: -0.0002

Data Index: 777624 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0952. Min Act: -0.0002

Data Index: 1159687 (C4 (Web Text))

Max Activating Token Index: 454

Text #16

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0881. Min Act: -0.0002

Data Index: 95153 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0921. Min Act: -0.0002

Data Index: 1011857 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0869. Min Act: -0.0002

Data Index: 339410 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0907. Min Act: -0.0002

Data Index: 1168304 (C4 (Web Text))

Max Activating Token Index: 38