Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4014 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.3170. Min Act: -0.0001

Data Index: 255023 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.3136. Min Act: -0.0001

Data Index: 477561 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2853. Min Act: -0.0001

Data Index: 526138 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2785. Min Act: -0.0001

Data Index: 647144 (C4 (Web Text))

Max Activating Token Index: 709

Text #4

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2774. Min Act: -0.0001

Data Index: 1061902 (C4 (Web Text))

Max Activating Token Index: 99

Text #5

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2655. Min Act: -0.0001

Data Index: 28657 (C4 (Web Text))

Max Activating Token Index: 815

Text #6

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2959. Min Act: -0.0001

Data Index: 912321 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2643. Min Act: -0.0001

Data Index: 806647 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2623. Min Act: -0.0001

Data Index: 81860 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2604. Min Act: -0.0001

Data Index: 443040 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2694. Min Act: -0.0001

Data Index: 643956 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2574. Min Act: -0.0001

Data Index: 1183405 (C4 (Web Text))

Max Activating Token Index: 267

Text #12

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2539. Min Act: -0.0001

Data Index: 688548 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2575. Min Act: -0.0001

Data Index: 912528 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2451. Min Act: -0.0000

Data Index: 631706 (C4 (Web Text))

Max Activating Token Index: 105

Text #15

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2334. Min Act: -0.0000

Data Index: 957387 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2443. Min Act: -0.0001

Data Index: 500637 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2525. Min Act: -0.0001

Data Index: 618390 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2431. Min Act: -0.0001

Data Index: 1309036 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 0.3170. Min Range: -0.3170

Max Act: 0.2402. Min Act: -0.0001

Data Index: 415659 (C4 (Web Text))

Max Activating Token Index: 776