Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 41 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2932. Min Range: -0.2932

Max Act: 0.2932. Min Act: -0.0001

Data Index: 617193 (C4 (Web Text))

Max Activating Token Index: 435

Text #1

Max Range: 0.2932. Min Range: -0.2932

Max Act: 0.2383. Min Act: -0.0001

Data Index: 56072 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 0.2932. Min Range: -0.2932

Max Act: 0.2280. Min Act: -0.0001

Data Index: 423129 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 0.2932. Min Range: -0.2932

Max Act: 0.2532. Min Act: -0.0001

Data Index: 401837 (C4 (Web Text))

Max Activating Token Index: 273

Text #4

Max Range: 0.2932. Min Range: -0.2932

Max Act: 0.2205. Min Act: -0.0001

Data Index: 961499 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 0.2932. Min Range: -0.2932

Max Act: 0.2339. Min Act: -0.0001

Data Index: 466898 (C4 (Web Text))

Max Activating Token Index: 782

Text #6

Max Range: 0.2932. Min Range: -0.2932

Max Act: 0.2162. Min Act: -0.0001

Data Index: 1302030 (C4 (Web Text))

Max Activating Token Index: 548

Text #7

Max Range: 0.2932. Min Range: -0.2932

Max Act: 0.2151. Min Act: -0.0001

Data Index: 241988 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 0.2932. Min Range: -0.2932

Max Act: 0.2175. Min Act: -0.0001

Data Index: 686183 (C4 (Web Text))

Max Activating Token Index: 413

Text #9

Max Range: 0.2932. Min Range: -0.2932

Max Act: 0.2215. Min Act: -0.0001

Data Index: 691450 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 0.2932. Min Range: -0.2932

Max Act: 0.2131. Min Act: -0.0001

Data Index: 989960 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 0.2932. Min Range: -0.2932

Max Act: 0.2089. Min Act: -0.0001

Data Index: 1332234 (C4 (Web Text))

Max Activating Token Index: 792

Text #12

Max Range: 0.2932. Min Range: -0.2932

Max Act: 0.2142. Min Act: -0.0001

Data Index: 1322685 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 0.2932. Min Range: -0.2932

Max Act: 0.2054. Min Act: -0.0001

Data Index: 165925 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 0.2932. Min Range: -0.2932

Max Act: 0.2043. Min Act: -0.0001

Data Index: 949336 (C4 (Web Text))

Max Activating Token Index: 330

Text #15

Max Range: 0.2932. Min Range: -0.2932

Max Act: 0.1963. Min Act: -0.0001

Data Index: 546251 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 0.2932. Min Range: -0.2932

Max Act: 0.2036. Min Act: -0.0001

Data Index: 147269 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 0.2932. Min Range: -0.2932

Max Act: 0.2102. Min Act: -0.0001

Data Index: 1004226 (C4 (Web Text))

Max Activating Token Index: 954

Text #18

Max Range: 0.2932. Min Range: -0.2932

Max Act: 0.1959. Min Act: -0.0001

Data Index: 291279 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 0.2932. Min Range: -0.2932

Max Act: 0.1942. Min Act: -0.0001

Data Index: 69038 (C4 (Web Text))

Max Activating Token Index: 767