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

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

Neuron 2305 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9393. Min Range: -0.9393

Max Act: 0.9162. Min Act: -0.0000

Data Index: 321580 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 0.9393. Min Range: -0.9393

Max Act: 0.9096. Min Act: -0.0000

Data Index: 1155633 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 0.9393. Min Range: -0.9393

Max Act: 0.8567. Min Act: -0.0000

Data Index: 627404 (C4 (Web Text))

Max Activating Token Index: 193

Text #3

Max Range: 0.9393. Min Range: -0.9393

Max Act: 0.9393. Min Act: -0.0000

Data Index: 1102574 (C4 (Web Text))

Max Activating Token Index: 198

Text #4

Max Range: 0.9393. Min Range: -0.9393

Max Act: 0.8815. Min Act: -0.0000

Data Index: 96216 (C4 (Web Text))

Max Activating Token Index: 142

Text #5

Max Range: 0.9393. Min Range: -0.9393

Max Act: 0.8280. Min Act: -0.0000

Data Index: 834526 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 0.9393. Min Range: -0.9393

Max Act: 0.8223. Min Act: -0.0000

Data Index: 476963 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 0.9393. Min Range: -0.9393

Max Act: 0.8298. Min Act: -0.0000

Data Index: 1208319 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 0.9393. Min Range: -0.9393

Max Act: 0.7829. Min Act: -0.0000

Data Index: 515222 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 0.9393. Min Range: -0.9393

Max Act: 0.7591. Min Act: -0.0000

Data Index: 685688 (C4 (Web Text))

Max Activating Token Index: 303

Text #10

Max Range: 0.9393. Min Range: -0.9393

Max Act: 0.7525. Min Act: -0.0000

Data Index: 333851 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 0.9393. Min Range: -0.9393

Max Act: 0.7768. Min Act: -0.0000

Data Index: 540600 (C4 (Web Text))

Max Activating Token Index: 390

Text #12

Max Range: 0.9393. Min Range: -0.9393

Max Act: 0.7281. Min Act: -0.0000

Data Index: 109640 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 0.9393. Min Range: -0.9393

Max Act: 0.6831. Min Act: -0.0000

Data Index: 1083296 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 0.9393. Min Range: -0.9393

Max Act: 0.7316. Min Act: -0.0000

Data Index: 323283 (C4 (Web Text))

Max Activating Token Index: 979

Text #15

Max Range: 0.9393. Min Range: -0.9393

Max Act: 0.7279. Min Act: -0.0000

Data Index: 1022911 (C4 (Web Text))

Max Activating Token Index: 593

Text #16

Max Range: 0.9393. Min Range: -0.9393

Max Act: 0.7268. Min Act: -0.0000

Data Index: 182791 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 0.9393. Min Range: -0.9393

Max Act: 0.7240. Min Act: -0.0000

Data Index: 615849 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 0.9393. Min Range: -0.9393

Max Act: 0.7183. Min Act: -0.0000

Data Index: 1279450 (C4 (Web Text))

Max Activating Token Index: 413

Text #19

Max Range: 0.9393. Min Range: -0.9393

Max Act: 0.7069. Min Act: -0.0000

Data Index: 61371 (C4 (Web Text))

Max Activating Token Index: 648