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

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

Neuron 1908 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8208. Min Range: -5.8208

Max Act: 5.8208. Min Act: -0.0000

Data Index: 992891 (C4 (Web Text))

Max Activating Token Index: 505

Text #1

Max Range: 5.8208. Min Range: -5.8208

Max Act: 5.5012. Min Act: -0.0000

Data Index: 253602 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 5.8208. Min Range: -5.8208

Max Act: 5.3028. Min Act: -0.0000

Data Index: 767674 (C4 (Web Text))

Max Activating Token Index: 389

Text #3

Max Range: 5.8208. Min Range: -5.8208

Max Act: 4.9559. Min Act: -0.0000

Data Index: 486869 (C4 (Web Text))

Max Activating Token Index: 805

Text #4

Max Range: 5.8208. Min Range: -5.8208

Max Act: 5.0794. Min Act: -0.0000

Data Index: 1194518 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 5.8208. Min Range: -5.8208

Max Act: 4.8885. Min Act: -0.0000

Data Index: 639799 (C4 (Web Text))

Max Activating Token Index: 713

Text #6

Max Range: 5.8208. Min Range: -5.8208

Max Act: 5.0074. Min Act: -0.0000

Data Index: 714568 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 5.8208. Min Range: -5.8208

Max Act: 4.5329. Min Act: -0.0000

Data Index: 439364 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 5.8208. Min Range: -5.8208

Max Act: 4.3880. Min Act: -0.0000

Data Index: 582817 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 5.8208. Min Range: -5.8208

Max Act: 3.8255. Min Act: -0.0000

Data Index: 892764 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 5.8208. Min Range: -5.8208

Max Act: 3.6071. Min Act: -0.0000

Data Index: 233187 (C4 (Web Text))

Max Activating Token Index: 471

Text #11

Max Range: 5.8208. Min Range: -5.8208

Max Act: 3.4409. Min Act: -0.0000

Data Index: 743497 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 5.8208. Min Range: -5.8208

Max Act: 3.5549. Min Act: -0.0000

Data Index: 1122818 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 5.8208. Min Range: -5.8208

Max Act: 3.2901. Min Act: -0.0000

Data Index: 995100 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 5.8208. Min Range: -5.8208

Max Act: 3.3296. Min Act: -0.0000

Data Index: 669083 (C4 (Web Text))

Max Activating Token Index: 236

Text #15

Max Range: 5.8208. Min Range: -5.8208

Max Act: 3.3081. Min Act: -0.0000

Data Index: 300931 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 5.8208. Min Range: -5.8208

Max Act: 3.1233. Min Act: -0.0000

Data Index: 1288083 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 5.8208. Min Range: -5.8208

Max Act: 3.2338. Min Act: -0.0000

Data Index: 270480 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 5.8208. Min Range: -5.8208

Max Act: 3.3835. Min Act: -0.0000

Data Index: 35304 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 5.8208. Min Range: -5.8208

Max Act: 3.1312. Min Act: -0.0000

Data Index: 843943 (C4 (Web Text))

Max Activating Token Index: 592