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

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

Neuron 4462 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5092. Min Range: -2.5092

Max Act: 2.5092. Min Act: -0.0000

Data Index: 919214 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 2.5092. Min Range: -2.5092

Max Act: 2.3876. Min Act: -0.0000

Data Index: 810166 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 2.5092. Min Range: -2.5092

Max Act: 2.1202. Min Act: -0.0000

Data Index: 1065463 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 2.5092. Min Range: -2.5092

Max Act: 2.1239. Min Act: -0.0000

Data Index: 442738 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 2.5092. Min Range: -2.5092

Max Act: 2.0659. Min Act: -0.0000

Data Index: 1015847 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 2.5092. Min Range: -2.5092

Max Act: 2.0512. Min Act: -0.0000

Data Index: 104726 (C4 (Web Text))

Max Activating Token Index: 209

Text #6

Max Range: 2.5092. Min Range: -2.5092

Max Act: 1.7992. Min Act: -0.0000

Data Index: 604205 (C4 (Web Text))

Max Activating Token Index: 721

Text #7

Max Range: 2.5092. Min Range: -2.5092

Max Act: 1.8280. Min Act: 0.0000

Data Index: 860275 (C4 (Web Text))

Max Activating Token Index: 836

Text #8

Max Range: 2.5092. Min Range: -2.5092

Max Act: 1.8922. Min Act: -0.0000

Data Index: 885321 (C4 (Web Text))

Max Activating Token Index: 633

Text #9

Max Range: 2.5092. Min Range: -2.5092

Max Act: 1.7197. Min Act: -0.0000

Data Index: 962321 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 2.5092. Min Range: -2.5092

Max Act: 1.8227. Min Act: -0.0000

Data Index: 786980 (C4 (Web Text))

Max Activating Token Index: 206

Text #11

Max Range: 2.5092. Min Range: -2.5092

Max Act: 1.7893. Min Act: -0.0000

Data Index: 1268044 (C4 (Web Text))

Max Activating Token Index: 919

Text #12

Max Range: 2.5092. Min Range: -2.5092

Max Act: 1.8250. Min Act: -0.0000

Data Index: 958462 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 2.5092. Min Range: -2.5092

Max Act: 1.8720. Min Act: -0.0000

Data Index: 289716 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 2.5092. Min Range: -2.5092

Max Act: 1.8084. Min Act: -0.0000

Data Index: 1095641 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 2.5092. Min Range: -2.5092

Max Act: 1.7496. Min Act: -0.0000

Data Index: 141808 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 2.5092. Min Range: -2.5092

Max Act: 1.8610. Min Act: -0.0000

Data Index: 1169229 (C4 (Web Text))

Max Activating Token Index: 666

Text #17

Max Range: 2.5092. Min Range: -2.5092

Max Act: 1.6648. Min Act: -0.0000

Data Index: 526121 (C4 (Web Text))

Max Activating Token Index: 435

Text #18

Max Range: 2.5092. Min Range: -2.5092

Max Act: 1.7265. Min Act: -0.0000

Data Index: 927437 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 2.5092. Min Range: -2.5092

Max Act: 1.7148. Min Act: -0.0000

Data Index: 936456 (C4 (Web Text))

Max Activating Token Index: 744