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

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

Neuron 3447 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.1997. Min Range: -3.1997

Max Act: 3.1997. Min Act: -0.0001

Data Index: 142350 (C4 (Web Text))

Max Activating Token Index: 442

Text #1

Max Range: 3.1997. Min Range: -3.1997

Max Act: 3.0873. Min Act: -0.0001

Data Index: 1046719 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 3.1997. Min Range: -3.1997

Max Act: 2.8539. Min Act: -0.0001

Data Index: 568038 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 3.1997. Min Range: -3.1997

Max Act: 3.0838. Min Act: -0.0001

Data Index: 743237 (C4 (Web Text))

Max Activating Token Index: 221

Text #4

Max Range: 3.1997. Min Range: -3.1997

Max Act: 2.8172. Min Act: -0.0001

Data Index: 13599 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 3.1997. Min Range: -3.1997

Max Act: 2.7535. Min Act: -0.0001

Data Index: 182501 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 3.1997. Min Range: -3.1997

Max Act: 2.8380. Min Act: -0.0001

Data Index: 1267274 (C4 (Web Text))

Max Activating Token Index: 856

Text #7

Max Range: 3.1997. Min Range: -3.1997

Max Act: 2.6751. Min Act: -0.0001

Data Index: 792045 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 3.1997. Min Range: -3.1997

Max Act: 2.4675. Min Act: -0.0001

Data Index: 730414 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 3.1997. Min Range: -3.1997

Max Act: 2.4773. Min Act: -0.0001

Data Index: 767895 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 3.1997. Min Range: -3.1997

Max Act: 2.4288. Min Act: -0.0001

Data Index: 258010 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 3.1997. Min Range: -3.1997

Max Act: 2.8061. Min Act: -0.0001

Data Index: 1302358 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 3.1997. Min Range: -3.1997

Max Act: 2.5527. Min Act: -0.0001

Data Index: 998422 (C4 (Web Text))

Max Activating Token Index: 288

Text #13

Max Range: 3.1997. Min Range: -3.1997

Max Act: 2.4701. Min Act: -0.0001

Data Index: 953193 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 3.1997. Min Range: -3.1997

Max Act: 2.4945. Min Act: -0.0001

Data Index: 791441 (C4 (Web Text))

Max Activating Token Index: 478

Text #15

Max Range: 3.1997. Min Range: -3.1997

Max Act: 2.3173. Min Act: -0.0001

Data Index: 314693 (C4 (Web Text))

Max Activating Token Index: 374

Text #16

Max Range: 3.1997. Min Range: -3.1997

Max Act: 2.0749. Min Act: -0.0001

Data Index: 76065 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 3.1997. Min Range: -3.1997

Max Act: 2.5281. Min Act: -0.0001

Data Index: 1129261 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 3.1997. Min Range: -3.1997

Max Act: 2.4702. Min Act: -0.0001

Data Index: 1133350 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 3.1997. Min Range: -3.1997

Max Act: 2.6444. Min Act: -0.0001

Data Index: 38432 (C4 (Web Text))

Max Activating Token Index: 187