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

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

Neuron 3740 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: 4.0369. Min Range: -4.0369

Max Act: 4.0369. Min Act: -0.0000

Data Index: 181494 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 4.0369. Min Range: -4.0369

Max Act: 3.7021. Min Act: -0.0000

Data Index: 222481 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 4.0369. Min Range: -4.0369

Max Act: 3.1585. Min Act: -0.0000

Data Index: 895283 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 4.0369. Min Range: -4.0369

Max Act: 3.2924. Min Act: -0.0000

Data Index: 946254 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 4.0369. Min Range: -4.0369

Max Act: 3.2758. Min Act: -0.0000

Data Index: 1140431 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 4.0369. Min Range: -4.0369

Max Act: 3.2839. Min Act: -0.0000

Data Index: 1345996 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 4.0369. Min Range: -4.0369

Max Act: 3.2478. Min Act: -0.0000

Data Index: 67582 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 4.0369. Min Range: -4.0369

Max Act: 3.2447. Min Act: -0.0000

Data Index: 194655 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 4.0369. Min Range: -4.0369

Max Act: 3.0449. Min Act: -0.0000

Data Index: 740176 (C4 (Web Text))

Max Activating Token Index: 342

Text #9

Max Range: 4.0369. Min Range: -4.0369

Max Act: 3.1065. Min Act: -0.0000

Data Index: 139873 (C4 (Web Text))

Max Activating Token Index: 400

Text #10

Max Range: 4.0369. Min Range: -4.0369

Max Act: 3.1049. Min Act: -0.0000

Data Index: 145709 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 4.0369. Min Range: -4.0369

Max Act: 3.0991. Min Act: -0.0000

Data Index: 97868 (C4 (Web Text))

Max Activating Token Index: 385

Text #12

Max Range: 4.0369. Min Range: -4.0369

Max Act: 3.1272. Min Act: -0.0000

Data Index: 1329184 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 4.0369. Min Range: -4.0369

Max Act: 2.9163. Min Act: -0.0000

Data Index: 989643 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 4.0369. Min Range: -4.0369

Max Act: 2.9181. Min Act: -0.0000

Data Index: 1312596 (C4 (Web Text))

Max Activating Token Index: 99

Text #15

Max Range: 4.0369. Min Range: -4.0369

Max Act: 2.9049. Min Act: -0.0000

Data Index: 776794 (C4 (Web Text))

Max Activating Token Index: 619

Text #16

Max Range: 4.0369. Min Range: -4.0369

Max Act: 2.7530. Min Act: -0.0000

Data Index: 224111 (C4 (Web Text))

Max Activating Token Index: 209

Text #17

Max Range: 4.0369. Min Range: -4.0369

Max Act: 2.9724. Min Act: -0.0000

Data Index: 609999 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 4.0369. Min Range: -4.0369

Max Act: 2.8076. Min Act: -0.0000

Data Index: 62241 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 4.0369. Min Range: -4.0369

Max Act: 2.7767. Min Act: -0.0000

Data Index: 1147197 (C4 (Web Text))

Max Activating Token Index: 705