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

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

Neuron 3180 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 9.3231. Min Range: -9.3231

Max Act: 9.3231. Min Act: -0.0000

Data Index: 1190619 (C4 (Web Text))

Max Activating Token Index: 184

Text #1

Max Range: 9.3231. Min Range: -9.3231

Max Act: 8.7409. Min Act: -0.0000

Data Index: 857702 (C4 (Web Text))

Max Activating Token Index: 989

Text #2

Max Range: 9.3231. Min Range: -9.3231

Max Act: 8.2591. Min Act: -0.0000

Data Index: 552892 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 9.3231. Min Range: -9.3231

Max Act: 8.3590. Min Act: -0.0000

Data Index: 279316 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 9.3231. Min Range: -9.3231

Max Act: 7.9251. Min Act: -0.0000

Data Index: 913599 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 9.3231. Min Range: -9.3231

Max Act: 8.2532. Min Act: -0.0000

Data Index: 1191864 (C4 (Web Text))

Max Activating Token Index: 614

Text #6

Max Range: 9.3231. Min Range: -9.3231

Max Act: 8.2141. Min Act: -0.0000

Data Index: 393755 (C4 (Web Text))

Max Activating Token Index: 926

Text #7

Max Range: 9.3231. Min Range: -9.3231

Max Act: 7.8864. Min Act: -0.0000

Data Index: 205091 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 9.3231. Min Range: -9.3231

Max Act: 8.0644. Min Act: -0.0000

Data Index: 633212 (C4 (Web Text))

Max Activating Token Index: 906

Text #9

Max Range: 9.3231. Min Range: -9.3231

Max Act: 8.0203. Min Act: -0.0000

Data Index: 897109 (C4 (Web Text))

Max Activating Token Index: 881

Text #10

Max Range: 9.3231. Min Range: -9.3231

Max Act: 8.1169. Min Act: -0.0000

Data Index: 198016 (C4 (Web Text))

Max Activating Token Index: 757

Text #11

Max Range: 9.3231. Min Range: -9.3231

Max Act: 7.9469. Min Act: -0.0000

Data Index: 248670 (C4 (Web Text))

Max Activating Token Index: 235

Text #12

Max Range: 9.3231. Min Range: -9.3231

Max Act: 8.1023. Min Act: -0.0000

Data Index: 35386 (C4 (Web Text))

Max Activating Token Index: 81

Text #13

Max Range: 9.3231. Min Range: -9.3231

Max Act: 7.9301. Min Act: -0.0000

Data Index: 1102011 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 9.3231. Min Range: -9.3231

Max Act: 8.0869. Min Act: -0.0000

Data Index: 1200309 (C4 (Web Text))

Max Activating Token Index: 729

Text #15

Max Range: 9.3231. Min Range: -9.3231

Max Act: 8.0874. Min Act: -0.0000

Data Index: 543776 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 9.3231. Min Range: -9.3231

Max Act: 8.0814. Min Act: -0.0000

Data Index: 860224 (C4 (Web Text))

Max Activating Token Index: 970

Text #17

Max Range: 9.3231. Min Range: -9.3231

Max Act: 8.4081. Min Act: -0.0000

Data Index: 644781 (C4 (Web Text))

Max Activating Token Index: 743

Text #18

Max Range: 9.3231. Min Range: -9.3231

Max Act: 7.9040. Min Act: -0.0000

Data Index: 124282 (C4 (Web Text))

Max Activating Token Index: 458

Text #19

Max Range: 9.3231. Min Range: -9.3231

Max Act: 7.7473. Min Act: -0.0000

Data Index: 185613 (C4 (Web Text))

Max Activating Token Index: 180