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

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

Neuron 3040 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3268. Min Range: -0.3268

Max Act: 0.3268. Min Act: -0.0001

Data Index: 127175 (C4 (Web Text))

Max Activating Token Index: 328

Text #1

Max Range: 0.3268. Min Range: -0.3268

Max Act: 0.2944. Min Act: -0.0001

Data Index: 226640 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 0.3268. Min Range: -0.3268

Max Act: 0.2959. Min Act: -0.0001

Data Index: 153605 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 0.3268. Min Range: -0.3268

Max Act: 0.3021. Min Act: -0.0001

Data Index: 856960 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 0.3268. Min Range: -0.3268

Max Act: 0.2845. Min Act: -0.0001

Data Index: 931187 (C4 (Web Text))

Max Activating Token Index: 1019

Text #5

Max Range: 0.3268. Min Range: -0.3268

Max Act: 0.2478. Min Act: -0.0001

Data Index: 821859 (C4 (Web Text))

Max Activating Token Index: 549

Text #6

Max Range: 0.3268. Min Range: -0.3268

Max Act: 0.2612. Min Act: -0.0001

Data Index: 262324 (C4 (Web Text))

Max Activating Token Index: 622

Text #7

Max Range: 0.3268. Min Range: -0.3268

Max Act: 0.2629. Min Act: -0.0001

Data Index: 958069 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 0.3268. Min Range: -0.3268

Max Act: 0.2635. Min Act: -0.0001

Data Index: 1112986 (C4 (Web Text))

Max Activating Token Index: 413

Text #9

Max Range: 0.3268. Min Range: -0.3268

Max Act: 0.2507. Min Act: -0.0001

Data Index: 1101853 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 0.3268. Min Range: -0.3268

Max Act: 0.2579. Min Act: -0.0001

Data Index: 841016 (C4 (Web Text))

Max Activating Token Index: 312

Text #11

Max Range: 0.3268. Min Range: -0.3268

Max Act: 0.2586. Min Act: -0.0001

Data Index: 1220455 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 0.3268. Min Range: -0.3268

Max Act: 0.2500. Min Act: -0.0001

Data Index: 1068334 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 0.3268. Min Range: -0.3268

Max Act: 0.2584. Min Act: -0.0001

Data Index: 1069979 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 0.3268. Min Range: -0.3268

Max Act: 0.2499. Min Act: -0.0001

Data Index: 507453 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 0.3268. Min Range: -0.3268

Max Act: 0.2568. Min Act: -0.0001

Data Index: 655034 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 0.3268. Min Range: -0.3268

Max Act: 0.2581. Min Act: -0.0001

Data Index: 778957 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 0.3268. Min Range: -0.3268

Max Act: 0.2486. Min Act: -0.0001

Data Index: 1276732 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 0.3268. Min Range: -0.3268

Max Act: 0.2456. Min Act: -0.0001

Data Index: 852237 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 0.3268. Min Range: -0.3268

Max Act: 0.2469. Min Act: -0.0001

Data Index: 415564 (C4 (Web Text))

Max Activating Token Index: 474