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

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

Neuron 538 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7408. Min Range: -0.7408

Max Act: 0.7408. Min Act: -0.0000

Data Index: 662324 (C4 (Web Text))

Max Activating Token Index: 790

Text #1

Max Range: 0.7408. Min Range: -0.7408

Max Act: 0.7372. Min Act: -0.0000

Data Index: 1313098 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 0.7408. Min Range: -0.7408

Max Act: 0.6713. Min Act: -0.0000

Data Index: 1187993 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 0.7408. Min Range: -0.7408

Max Act: 0.6565. Min Act: -0.0000

Data Index: 1233877 (C4 (Web Text))

Max Activating Token Index: 950

Text #4

Max Range: 0.7408. Min Range: -0.7408

Max Act: 0.6223. Min Act: -0.0000

Data Index: 847498 (C4 (Web Text))

Max Activating Token Index: 628

Text #5

Max Range: 0.7408. Min Range: -0.7408

Max Act: 0.6457. Min Act: -0.0000

Data Index: 900832 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 0.7408. Min Range: -0.7408

Max Act: 0.6322. Min Act: -0.0000

Data Index: 429656 (C4 (Web Text))

Max Activating Token Index: 824

Text #7

Max Range: 0.7408. Min Range: -0.7408

Max Act: 0.6280. Min Act: -0.0000

Data Index: 1164118 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 0.7408. Min Range: -0.7408

Max Act: 0.6186. Min Act: -0.0001

Data Index: 805350 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 0.7408. Min Range: -0.7408

Max Act: 0.6122. Min Act: -0.0000

Data Index: 1019953 (C4 (Web Text))

Max Activating Token Index: 178

Text #10

Max Range: 0.7408. Min Range: -0.7408

Max Act: 0.5851. Min Act: -0.0000

Data Index: 220051 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 0.7408. Min Range: -0.7408

Max Act: 0.6228. Min Act: -0.0000

Data Index: 487937 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 0.7408. Min Range: -0.7408

Max Act: 0.5610. Min Act: -0.0000

Data Index: 6859 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 0.7408. Min Range: -0.7408

Max Act: 0.5908. Min Act: -0.0000

Data Index: 1245803 (C4 (Web Text))

Max Activating Token Index: 887

Text #14

Max Range: 0.7408. Min Range: -0.7408

Max Act: 0.5925. Min Act: -0.0000

Data Index: 980589 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 0.7408. Min Range: -0.7408

Max Act: 0.6093. Min Act: -0.0000

Data Index: 999033 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 0.7408. Min Range: -0.7408

Max Act: 0.5601. Min Act: -0.0000

Data Index: 933686 (C4 (Web Text))

Max Activating Token Index: 582

Text #17

Max Range: 0.7408. Min Range: -0.7408

Max Act: 0.5785. Min Act: -0.0000

Data Index: 155322 (C4 (Web Text))

Max Activating Token Index: 236

Text #18

Max Range: 0.7408. Min Range: -0.7408

Max Act: 0.5702. Min Act: -0.0000

Data Index: 1322670 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 0.7408. Min Range: -0.7408

Max Act: 0.5664. Min Act: 0.0001

Data Index: 526132 (C4 (Web Text))

Max Activating Token Index: 977