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

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

Neuron 3636 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6799. Min Range: -1.6799

Max Act: 1.6799. Min Act: -0.0000

Data Index: 839995 (C4 (Web Text))

Max Activating Token Index: 419

Text #1

Max Range: 1.6799. Min Range: -1.6799

Max Act: 1.5341. Min Act: -0.0000

Data Index: 652633 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 1.6799. Min Range: -1.6799

Max Act: 1.5248. Min Act: -0.0000

Data Index: 107001 (C4 (Web Text))

Max Activating Token Index: 186

Text #3

Max Range: 1.6799. Min Range: -1.6799

Max Act: 1.5151. Min Act: -0.0000

Data Index: 662578 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 1.6799. Min Range: -1.6799

Max Act: 1.4890. Min Act: -0.0000

Data Index: 65565 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 1.6799. Min Range: -1.6799

Max Act: 1.5714. Min Act: -0.0000

Data Index: 1194720 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 1.6799. Min Range: -1.6799

Max Act: 1.4817. Min Act: -0.0000

Data Index: 337311 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 1.6799. Min Range: -1.6799

Max Act: 1.4609. Min Act: -0.0000

Data Index: 230676 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 1.6799. Min Range: -1.6799

Max Act: 1.4139. Min Act: -0.0000

Data Index: 658685 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 1.6799. Min Range: -1.6799

Max Act: 1.3989. Min Act: -0.0000

Data Index: 1274963 (C4 (Web Text))

Max Activating Token Index: 87

Text #10

Max Range: 1.6799. Min Range: -1.6799

Max Act: 1.3246. Min Act: -0.0000

Data Index: 272087 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 1.6799. Min Range: -1.6799

Max Act: 1.3233. Min Act: -0.0000

Data Index: 1305007 (C4 (Web Text))

Max Activating Token Index: 559

Text #12

Max Range: 1.6799. Min Range: -1.6799

Max Act: 1.3868. Min Act: -0.0000

Data Index: 1117420 (C4 (Web Text))

Max Activating Token Index: 861

Text #13

Max Range: 1.6799. Min Range: -1.6799

Max Act: 1.2958. Min Act: -0.0000

Data Index: 137465 (C4 (Web Text))

Max Activating Token Index: 943

Text #14

Max Range: 1.6799. Min Range: -1.6799

Max Act: 1.2750. Min Act: -0.0000

Data Index: 198047 (C4 (Web Text))

Max Activating Token Index: 255

Text #15

Max Range: 1.6799. Min Range: -1.6799

Max Act: 1.2884. Min Act: -0.0000

Data Index: 248391 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 1.6799. Min Range: -1.6799

Max Act: 1.3680. Min Act: -0.0000

Data Index: 21895 (C4 (Web Text))

Max Activating Token Index: 400

Text #17

Max Range: 1.6799. Min Range: -1.6799

Max Act: 1.2041. Min Act: -0.0000

Data Index: 546209 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 1.6799. Min Range: -1.6799

Max Act: 1.3670. Min Act: -0.0000

Data Index: 34157 (C4 (Web Text))

Max Activating Token Index: 986

Text #19

Max Range: 1.6799. Min Range: -1.6799

Max Act: 1.2705. Min Act: -0.0000

Data Index: 488458 (C4 (Web Text))

Max Activating Token Index: 742