Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4822 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.7934. Min Act: -0.0000

Data Index: 719852 (C4 (Web Text))

Max Activating Token Index: 277

Text #1

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.7191. Min Act: -0.0000

Data Index: 170592 (C4 (Web Text))

Max Activating Token Index: 420

Text #2

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.7153. Min Act: -0.0000

Data Index: 971641 (C4 (Web Text))

Max Activating Token Index: 156

Text #3

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.7190. Min Act: -0.0000

Data Index: 112456 (C4 (Web Text))

Max Activating Token Index: 117

Text #4

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.7181. Min Act: -0.0000

Data Index: 903367 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.7267. Min Act: -0.0000

Data Index: 428353 (C4 (Web Text))

Max Activating Token Index: 616

Text #6

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.6874. Min Act: -0.0001

Data Index: 1438666 (Python Code)

Max Activating Token Index: 94

Text #7

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.7018. Min Act: -0.0000

Data Index: 1175691 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.6686. Min Act: -0.0000

Data Index: 1236312 (C4 (Web Text))

Max Activating Token Index: 906

Text #9

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.6865. Min Act: -0.0000

Data Index: 1449731 (Python Code)

Max Activating Token Index: 121

Text #10

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.6496. Min Act: -0.0000

Data Index: 457054 (C4 (Web Text))

Max Activating Token Index: 283

Text #11

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.5927. Min Act: -0.0000

Data Index: 1371171 (Python Code)

Max Activating Token Index: 300

Text #12

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.6420. Min Act: -0.0000

Data Index: 938427 (C4 (Web Text))

Max Activating Token Index: 1005

Text #13

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.5974. Min Act: -0.0000

Data Index: 493429 (C4 (Web Text))

Max Activating Token Index: 924

Text #14

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.5750. Min Act: -0.0000

Data Index: 76987 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.6250. Min Act: -0.0000

Data Index: 1493520 (Python Code)

Max Activating Token Index: 206

Text #16

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.5485. Min Act: -0.0000

Data Index: 1353763 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.5920. Min Act: -0.0000

Data Index: 1061452 (C4 (Web Text))

Max Activating Token Index: 681

Text #18

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.5760. Min Act: -0.0001

Data Index: 193898 (C4 (Web Text))

Max Activating Token Index: 764

Text #19

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.5611. Min Act: -0.0000

Data Index: 1195038 (C4 (Web Text))

Max Activating Token Index: 155